© 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. 24-GEMMASCOPE-RES-16K
    11. 8364
    Prev
    Next
    INDEX
    Explanations

    the presence of opening and closing curly braces

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

    LaTeX environments

    np_acts-logits-general · gemini-2.0-flash

    LaTeX math formatting

    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
    /
    -0.52
    ...
    -0.51
    -
    -0.49
    …
    -0.49
    ,
    -0.49
    </blockquote>
    -0.48
     basic
    -0.47
     .
    -0.47
     ’
    -0.46
     The
    -0.46
    POSITIVE LOGITS
    center
    1.25
    itemize
    1.25
    enumerate
    1.21
    enumi
    1.09
    CJK
    0.93
    displayquote
    0.89
    abstract
    0.87
    tagHelperRunner
    0.84
    tabular
    0.82
     صوتيه
    0.81
    Activations Density 0.016%

    No Known Activations