© 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. 7977
    Prev
    Next
    INDEX
    Explanations

    modeling terms and statistical methods related to data analysis

    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
    SequentialGroup
    -0.36
    لينكات
    -0.34
    AxisSize
    -0.34
    Gera
    -0.32
    خواندن
    -0.32
    empre
    -0.32
    蚪
    -0.32
    Renew
    -0.31
    Caret
    -0.31
    cesis
    -0.31
    POSITIVE LOGITS
     account
    1.66
     accounted
    1.52
     accounting
    1.44
     accounts
    1.38
     factored
    1.37
     factoring
    1.34
     Account
    1.30
     ACCOUNT
    1.29
     учиты
    1.27
     incorporate
    1.25
    Activations Density 1.341%

    No Known Activations