© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 8477
    Prev
    Next
    INDEX
    Explanations

    key terms and references related to specific systems, characters, or entities associated with different contexts or subjects

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

    Tokens preceding a capitalized name

    np_acts-logits-general · gemini-2.0-flash

    josephson, orange uses, Leicester residents

    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
     FileWriter
    -0.57
    лябин
    -0.56
    copg
    -0.49
    ilever
    -0.48
    quiao
    -0.48
    athione
    -0.47
     Deere
    -0.47
     psycopg
    -0.46
    dataclass
    -0.46
    MultipartFile
    -0.46
    POSITIVE LOGITS
     Beaumont
    0.77
     resourceCulture
    0.58
     Clifton
    0.57
     Diener
    0.54
    bibfnamefont
    0.54
     Colonna
    0.53
     Caldwell
    0.53
    Medium
    0.53
     Duval
    0.53
     Benson
    0.52
    Activations Density 2.085%

    No Known Activations