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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 7754
    Prev
    Next
    INDEX
    Explanations

    coding concepts related to syntax and function declarations in programming

    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
    +#+
    -0.50
     transfieras
    -0.46
    OGND
    -0.45
    tagHelperRunner
    -0.45
    httphttps
    -0.44
    MLLoader
    -0.43
     unknownFields
    -0.42
     typelib
    -0.42
    findpost
    -0.42
    estacks
    -0.41
    POSITIVE LOGITS
     identifier
    0.51
     Identifier
    0.50
    Opening
    0.49
     assignment
    0.47
     Opening
    0.47
     expression
    0.46
    Identifier
    0.44
     opening
    0.44
     IDENT
    0.44
     Assignment
    0.42
    Activations Density 0.617%

    No Known Activations