Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 6315
    Prev
    Next
    INDEX
    Explanations

    JSON structure elements and key-value pairs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code, symbols, and special characters

    np_acts-logits-general · gemini-2.0-flash

    code snippets and structured text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     "
    -0.41
    ">(</
    -0.40
    “
    -0.36
     ๆ
    -0.36
    ệc
    -0.36
    料
    -0.35
    x
    -0.34
    //
    -0.33
     of
    -0.33
    <strong>
    -0.33
    POSITIVE LOGITS
    transQ
    0.86
    =['
    0.84
     queſta
    0.82
    ":{"
    0.82
    RegressionTest
    0.82
    :['
    0.81
     "','
    0.79
    StructEnd
    0.79
    addCriterion
    0.77
    ->___
    0.77
    Activations Density 0.443%

    No Known Activations