© 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 - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 10730
    Prev
    Next
    INDEX
    Explanations

    references to statements and declarations in various contexts

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

    "statement" and its context

    np_acts-logits-general · gemini-2.0-flash

    statement followed by punctuation or context

    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
     כול
    -0.57
     незавершена
    -0.51
    ClassNotFound
    -0.50
    Christians
    -0.49
    GeoNames
    -0.49
    Popularity
    -0.49
    inherits
    -0.48
     cận
    -0.48
    rrggbb
    -0.48
     Jody
    -0.47
    POSITIVE LOGITS
     statement
    2.27
     Statement
    2.13
    Statement
    2.00
     statements
    1.98
     STATEMENT
    1.96
    statement
    1.89
     Statements
    1.83
    STATEMENT
    1.73
    Statements
    1.66
    statements
    1.59
    Activations Density 0.181%

    No Known Activations