© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 7156
    Prev
    Next
    INDEX
    Explanations

    references to power dynamics and strength in characters or entities within a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to increased power or strength.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou

    phrases describing military strength, power, or superior capabilities.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    statements about power or strength levels and rankings, especially increases, regaining, or comparative superiority/equality in combat or capability.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defaultstate
    -0.66
     '\\;'
    -0.59
    delwed
    -0.55
    Gön
    -0.52
    ########.
    -0.49
    fillType
    -0.48
    Gruss
    -0.48
     typelib
    -0.48
     ProtoMessage
    -0.47
    цездатний
    -0.46
    POSITIVE LOGITS
     strength
    2.25
    strength
    1.91
    Strength
    1.80
     Strength
    1.78
     powerful
    1.76
     STRENGTH
    1.72
     stronger
    1.62
     power
    1.56
    powerful
    1.56
     kekuatan
    1.55
    Activations Density 0.463%

    No Known Activations