© 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. 9968
    Prev
    Next
    INDEX
    Explanations

    legal terms and references related to court cases and decisions

    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
     '\\;'
    -0.50
    LookAnd
    -0.38
    ItemBackground
    -0.35
    يكب
    -0.33
    tanleria
    -0.33
    Panamoan
    -0.30
     Paglinawan
    -0.29
    Дереккөздер
    -0.29
    Ārējās
    -0.28
    ArrowToggle
    -0.27
    POSITIVE LOGITS
     October
    2.95
     September
    2.95
     July
    2.94
     February
    2.92
     December
    2.91
     November
    2.89
     April
    2.86
     June
    2.86
     January
    2.83
     August
    2.77
    Activations Density 3.598%

    No Known Activations