© 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. 31-GEMMASCOPE-RES-16K
    11. 4333
    Prev
    Next
    INDEX
    Explanations

    references to political or social conflicts and dynamics

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

    sudden changes or contrasts in situations (things that worked before but stopped working, or behaviors that changed abruptly).

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    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
     onBind
    -0.48
    riwal
    -0.47
    今回も
    -0.46
    ########.
    -0.44
     continuará
    -0.42
     onCancelled
    -0.40
    UnusedPrivate
    -0.40
    ostante
    -0.39
    tagHelperRunner
    -0.39
    godic
    -0.39
    POSITIVE LOGITS
     suddenly
    3.75
    suddenly
    3.28
     Suddenly
    3.23
    Suddenly
    3.13
     sudden
    3.03
     plötzlich
    2.77
     soudain
    2.63
    突然
    2.47
    Sudden
    2.33
     Sudden
    2.30
    Activations Density 0.667%

    No Known Activations