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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 120107
    Prev
    Next
    INDEX
    Explanations

    complex mathematical expressions or high-level algorithms

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

    HTML tags and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    niſſe
    -0.93
    IntoConstraints
    -0.87
     surla
    -0.84
    ConstraintMaker
    -0.83
    AnchorStyles
    -0.81
    <unused8>
    -0.80
    <unused43>
    -0.80
    <unused52>
    -0.80
    <unused41>
    -0.80
    <unused16>
    -0.80
    POSITIVE LOGITS
    <strong>
    0.45
    1
    0.44
    <em>
    0.40
    The
    0.37
    <code>
    0.37
    ↵↵
    0.35
    2
    0.35
    <b>
    0.35
    0
    0.34
    ↵
    0.33
    Activations Density 0.000%

    No Known Activations