© 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-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 3832
    Prev
    Next
    INDEX
    Explanations

    special characters or formatting symbols commonly used in text

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

    Text surrounded by asterisks

    np_acts-logits-general · gemini-2.0-flash

    * (asterisk) or related special tokens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zeera
    -0.75
    addGap
    -0.74
     copro
    -0.70
    hasMoreElements
    -0.66
    readFileSync
    -0.62
     Gren
    -0.61
    gridx
    -0.61
    ondale
    -0.61
    ==",
    -0.61
    della
    -0.60
    POSITIVE LOGITS
    ***********
    1.19
    **********
    1.19
    *********
    1.18
     *
    1.18
    *************
    1.16
    ********
    1.11
    :*
    1.11
    ?*
    1.11
    ************
    1.11
    ()*
    1.10
    Activations Density 0.808%

    No Known Activations