© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 11997
    Prev
    Next
    INDEX
    Explanations

    numerical data and measurements related to experiments or studies

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

    Numbers as standalone values

    np_acts-logits-general · gemini-2.0-flash

    numbers and units

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    .
    -0.44
     by
    -0.34
     during
    -0.33
     that
    -0.33
     for
    -0.32
     to
    -0.29
    <strong>
    -0.29
    ↵↵
    -0.29
     while
    -0.29
    The
    -0.29
    POSITIVE LOGITS
    enablog
    1.18
    <unused14>
    1.15
    <unused68>
    1.15
     zwiſchen
    1.15
    <unused41>
    1.15
    [@BOS@]
    1.15
    ſſung
    1.15
    <unused79>
    1.15
    <unused51>
    1.15
    <unused3>
    1.14
    Activations Density 1.471%

    No Known Activations