Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 82435
    Prev
    Next
    INDEX
    Explanations

    references to a 'model' in a legal or regulatory context

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

    model lease

    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
    mis
    -0.36
    est
    -0.36
    u
    -0.34
     –
    -0.34
    –
    -0.32
    Sur
    -0.32
     mis
    -0.31
    til
    -0.31
    sur
    -0.31
     committed
    -0.31
    POSITIVE LOGITS
     tartalomajánló
    0.92
    WebElementEntity
    0.91
    ьаж
    0.84
     ब्रेकडाउन
    0.83
     ***!
    0.83
    SourceChecksum
    0.83
    parsedMessage
    0.79
    verwijspagina
    0.78
    ьажоргаш
    0.78
    MigrationBuilder
    0.77
    Activations Density 0.000%

    No Known Activations