© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 7339
    Prev
    Next
    INDEX
    Explanations

    diverse punctuation and their contextual significance in documenting conversations or testimonies

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

    Tokens preceding parenthetical remarks or added phrases

    np_acts-logits-general · gemini-2.0-flash

    respectively, thus, etc

    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
    ,
    -1.99
    :
    -1.21
    .
    -1.16
    ?
    -1.10
    "
    -1.06
    /
    -1.04
    ;
    -1.02
    ...
    -0.94
    -
    -0.92
    (
    -0.91
    POSITIVE LOGITS
     etc
    1.22
     but
    1.09
     which
    1.07
     however
    1.05
     albeit
    1.05
     namely
    1.05
     including
    1.03
    etc
    1.03
     }}$,
    0.96
     although
    0.95
    Activations Density 2.944%

    No Known Activations