© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 7528
    Prev
    Next
    INDEX
    Explanations

    expressions of confusion or difficulty in understanding technology or software

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     did
    -0.46
     do
    -0.42
     only
    -0.39
     Did
    -0.37
    只需
    -0.36
     Only
    -0.34
     no
    -0.34
    Did
    -0.31
    only
    -0.31
    还可以
    -0.31
    POSITIVE LOGITS
    elemField
    0.77
    EDEFAULT
    0.65
    InitVars
    0.63
    ExtendWith
    0.63
     Roskov
    0.62
    principalColumn
    0.61
    GenerationType
    0.61
     BorderSide
    0.60
     BytesLike
    0.60
    पया
    0.59
    Activations Density 0.109%

    No Known Activations