© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 2560
    Prev
    Next
    INDEX
    Explanations

    coding-related syntax and structures

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

    "<end_of_turn>" token

    np_acts-logits-general · gemini-2.0-flash

    code and mathematical notation

    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
     MainAxisSize
    -0.52
    UnusedPrivate
    -0.51
    .*")]
    -0.50
     ModelExpression
    -0.50
    adpleegd
    -0.50
     defaultstate
    -0.49
    principalColumn
    -0.49
     initComponents
    -0.49
    
    -0.48
     الحره
    -0.47
    POSITIVE LOGITS
     Brau
    0.47
    tlement
    0.38
     Jasa
    0.37
    uscitation
    0.36
    addPreferred
    0.36
    &=&\
    0.36
    igur
    0.36
    ureen
    0.36
    brale
    0.36
    Gren
    0.36
    Activations Density 1.599%

    No Known Activations