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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 9216
    Prev
    Next
    INDEX
    Explanations

    dialogue that conveys a demand or request for clarification

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

    Quotation marks

    np_acts-logits-general · gemini-2.0-flash

    quotation marks and dialogue

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __':
    -0.81
    '],
    -0.70
    !';
    -0.69
     Архів
    -0.69
     .)
    -0.69
    ...');
    -0.69
     **/
    -0.67
    __':
    -0.66
    !')
    -0.66
     Wikimedijinoj
    -0.65
    POSITIVE LOGITS
    “
    3.19
    "
    2.48
     “
    2.33
    ”
    2.11
    “[
    1.95
    “(
    1.91
     "
    1.88
    “…
    1.84
    「
    1.76
    “...
    1.69
    Activations Density 0.209%

    No Known Activations