© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 8325
    Prev
    Next
    INDEX
    Explanations

    elements related to the existence or requirements of entities and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    دانشنامهٔ
    -0.65
    GOTREF
    -0.41
     snippetHide
    -0.37
    postsleuth
    -0.36
    jsxFileName
    -0.35
    Beg
    -0.35
    MessageWindow
    -0.35
    ACHUSET
    -0.35
     TType
    -0.35
    phany
    -0.35
    POSITIVE LOGITS
     able
    2.81
     ability
    2.14
     Able
    1.85
    Able
    1.84
     capaz
    1.81
     Ability
    1.74
    Ability
    1.65
     schop
    1.59
     capables
    1.49
     capable
    1.48
    Activations Density 0.629%

    No Known Activations