© 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. 4251
    Prev
    Next
    INDEX
    Explanations

    structured data elements and patterns in a JSON-like format

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

    Characters often found in code or scripts

    np_acts-logits-general · gemini-2.0-flash

    mounted disk

    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
     ../
    -0.56
    (.
    -0.48
    (__('
    -0.47
     kří
    -0.47
     McCabe
    -0.47
     ../../
    -0.46
    lah
    -0.45
     Cognition
    -0.45
     ASSIGN
    -0.44
     implied
    -0.43
    POSITIVE LOGITS
    )".
    0.74
    ."</
    0.72
    )”.
    0.72
    "</
    0.68
    '".
    0.67
    ”!
    0.66
    "?
    0.65
    Rujuakan
    0.65
    )":
    0.65
    __":
    0.65
    Activations Density 0.091%

    No Known Activations