© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 9385
    Prev
    Next
    INDEX
    Explanations

    references to power, empowerment, and transformation

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

    Acquiring power/strength

    np_acts-logits-general · gemini-2.0-flash

    power and strength

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Slf
    -0.53
    AnchorTagHelper
    -0.48
    !*\
    -0.48
    WriteBarrier
    -0.46
    Tracce
    -0.46
    fjspx
    -0.45
     Signalez
    -0.45
    HostException
    -0.44
     parseFrom
    -0.42
    DataMember
    -0.42
    POSITIVE LOGITS
     empower
    0.76
     empowered
    0.75
     empowers
    0.71
     empowering
    0.70
     equip
    0.68
     armed
    0.68
    Equip
    0.67
     equipping
    0.67
     empowerment
    0.66
     equipped
    0.65
    Activations Density 0.448%

    No Known Activations