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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6868
    Prev
    Next
    INDEX
    Explanations

    references to legal statutes and procedures in criminal law

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

    28 u.s.c. section

    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
     cuesta
    -0.33
     Komunikasi
    -0.32
    ]--;
    -0.31
     templado
    -0.31
     quedarse
    -0.30
     recaud
    -0.29
     presion
    -0.29
     avanzado
    -0.29
    postsleuth
    -0.29
     Trabajo
    -0.29
    POSITIVE LOGITS
    IntoConstraints
    0.78
     pinulongan
    0.64
    :+:
    0.60
    makeConstraints
    0.60
    adaptiveStyles
    0.59
     disambiguazione
    0.59
    NullException
    0.58
    extAlignment
    0.58
    ########.
    0.57
    HMIS
    0.57
    Activations Density 0.018%

    No Known Activations