© 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
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 12401
    Prev
    Next
    INDEX
    Explanations

    terms and references related to colons and colon-related concepts

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

    starting with "Col" or "col"

    np_acts-logits-general · gemini-2.0-flash

    starts with col

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Rptr
    -0.70
    AndEndTag
    -0.62
     BorderRadius
    -0.59
    bootstrapcdn
    -0.55
     wireType
    -0.54
    UpInside
    -0.53
    Παραπομπές
    -0.52
     Rptr
    -0.51
    Demografía
    -0.51
    Démographie
    -0.51
    POSITIVE LOGITS
     col
    0.61
     Col
    0.59
    Col
    0.57
    col
    0.52
     COL
    0.49
     COLL
    0.47
    COL
    0.42
     Colla
    0.42
     Cole
    0.40
     autorytatywna
    0.39
    Activations Density 0.246%

    No Known Activations