© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 5545
    Prev
    Next
    INDEX
    Explanations

    terms related to biological functions and gene expression

    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
    argout
    -0.53
    ✭✭
    -0.39
    InitStruct
    -0.37
     jadx
    -0.36
    efeated
    -0.34
    показания
    -0.32
    OGND
    -0.31
    mentaux
    -0.31
     лиш
    -0.31
    ometrial
    -0.29
    POSITIVE LOGITS
     specific
    3.81
     Specific
    3.48
    specific
    3.47
    Specific
    3.44
     SPECIFIC
    3.36
     specifically
    3.27
    SPECIFIC
    3.16
     específico
    2.97
    Specifically
    2.92
     Specifically
    2.88
    Activations Density 2.196%

    No Known Activations