© 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. 38-GEMMASCOPE-RES-16K
    6. 8408
    Prev
    Next
    INDEX
    Explanations

    names and identifiers related to legal cases and proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Мексичка
    -0.56
    UrlResolution
    -0.49
    DockStyle
    -0.49
    المكان
    -0.48
    InitVars
    -0.45
     насељу
    -0.45
    denly
    -0.42
     powinny
    -0.42
    siamo
    -0.42
     powinno
    -0.42
    POSITIVE LOGITS
     previously
    0.83
     sebelumnya
    0.66
    previously
    0.66
     said
    0.65
     tweeted
    0.64
     joins
    0.62
     anteriormente
    0.62
     eerder
    0.60
     told
    0.60
     recently
    0.60
    Activations Density 0.435%

    No Known Activations