© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 36893
    Prev
    Next
    INDEX
    Explanations

    expressions of subjective opinions and evaluations

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

    case, this time, sometimes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     lenker
    -0.63
    tagHelperRunner
    -0.58
    enetrable
    -0.54
    AntiForgeryToken
    -0.53
    #+#
    -0.52
    íncia
    -0.51
     ProtoMessage
    -0.50
    ynb
    -0.49
    popd
    -0.49
     beſti
    -0.49
    POSITIVE LOGITS
    今回も
    0.74
    今回の
    0.72
    今回
    0.70
    今回は
    0.62
    Case
    0.55
     przypadku
    0.54
    何况
    0.54
    Sometimes
    0.53
    这次
    0.52
     Case
    0.52
    Activations Density 0.110%

    No Known Activations