© 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. 5354
    Prev
    Next
    INDEX
    Explanations

    names of individuals and related artistic or cultural contributions

    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
    
    -0.48
     defStyle
    -0.44
    endphp
    -0.42
    astéroïdes
    -0.42
     CURIAM
    -0.40
     phosp
    -0.37
    instellungen
    -0.36
    imdi
    -0.36
    tanleria
    -0.36
     impregnated
    -0.35
    POSITIVE LOGITS
    tagHelperRunner
    0.81
     فريبيس
    0.61
    原始内容存档于
    0.54
     surla
    0.53
     AssemblyProduct
    0.50
     Administrativna
    0.49
    WillAppear
    0.49
    posedge
    0.45
    Artists
    0.44
    ImageContext
    0.43
    Activations Density 0.311%

    No Known Activations