© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 30962
    Prev
    Next
    INDEX
    Explanations

    code-related keywords and structure, particularly access modifiers and class definitions

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

    code keywords in sequence

    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
    pet
    -0.28
     lequel
    -0.26
     convierten
    -0.25
    രിക്ക
    -0.24
    ing
    -0.24
    </h3>
    -0.24
     käyt
    -0.23
    เ
    -0.23
     lesquelles
    -0.23
     coleta
    -0.23
    POSITIVE LOGITS
    Tikang
    0.93
    AndEndTag
    0.88
    GraphicsUnit
    0.86
     queſta
    0.84
    Portale
    0.84
    GEBURTSDATUM
    0.83
    Autoritní
    0.83
    sizeCache
    0.83
    存于互联网档案馆
    0.82
    ſicht
    0.81
    Activations Density 0.010%

    No Known Activations