© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 101034
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and syntax

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

    math formatting and variables

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    ,
    -0.38
    ↵↵
    -0.36
    <eos>
    -0.35
    <sup>
    -0.32
     מע
    -0.31
    <i>
    -0.28
    <em>
    -0.28
     Gesch
    -0.27
    -
    -0.27
     –
    -0.26
    POSITIVE LOGITS
    <unused14>
    1.19
    [@BOS@]
    1.19
    <unused74>
    1.19
    <unused79>
    1.19
    <unused41>
    1.19
    <unused52>
    1.19
    <unused17>
    1.18
    <unused23>
    1.18
    <unused16>
    1.18
    <unused8>
    1.18
    Activations Density 0.054%

    No Known Activations