© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 2637
    Prev
    Next
    INDEX
    Explanations

    words related to the process of reviewing or evaluating

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

    the + noun phrases

    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
    EDEFAULT
    -0.56
    Personensuche
    -0.49
     abstrait
    -0.46
     OMITBAD
    -0.44
    difficulty
    -0.44
     murales
    -0.42
     boire
    -0.41
    Usual
    -0.41
    StoreMessageInfo
    -0.41
     fön
    -0.40
    POSITIVE LOGITS
     retrieved
    0.80
     transferred
    0.80
     successfully
    0.79
     collected
    0.77
     recovered
    0.75
     cleared
    0.75
     completed
    0.74
     manipulated
    0.72
     accommodated
    0.72
     resolved
    0.71
    Activations Density 0.229%

    No Known Activations