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

    Neuronpedia

    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 - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 41921
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and special characters

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

    dashboard directive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.35
    getMenuInflater
    -0.32
    findpost
    -0.31
     jadx
    -0.30
     continúas
    -0.30
    lighet
    -0.29
     ferons
    -0.27
    ECONDS
    -0.27
     Justiz
    -0.27
     demonios
    -0.27
    POSITIVE LOGITS
    orianCalendar
    0.66
    AndView
    0.60
    CloseOperation
    0.59
    \{\\
    0.58
    ISupport
    0.56
     StringTokenizer
    0.55
    notic
    0.54
    AccessorTable
    0.53
    AnchorStyles
    0.53
    apsed
    0.52
    Activations Density 0.001%

    No Known Activations