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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 6163
    Prev
    Next
    INDEX
    Explanations

    HTML and CSS classes related to layout and structure

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

    The token "col" and related terms

    np_acts-logits-general · gemini-2.0-flash

    col

    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
     noDo
    -0.53
    ///</
    -0.45
     présidenti
    -0.45
    Jeografia
    -0.41
     Njema
    -0.41
     الرياضيه
    -0.39
     gdyby
    -0.39
    weetened
    -0.39
    (!__
    -0.39
     sueño
    -0.38
    POSITIVE LOGITS
    col
    2.48
     col
    2.47
    Col
    2.28
     Col
    2.23
     COL
    1.91
    COL
    1.89
     cols
    1.66
    cols
    1.59
    Cols
    1.56
     kol
    1.48
    Activations Density 0.071%

    No Known Activations