© 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. 16183
    Prev
    Next
    INDEX
    Explanations

    key programming constructs and function calls related to threading and error handling

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

    Code snippets containing parentheses and symbols

    np_acts-logits-general · gemini-2.0-flash

    == operator

    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
     Wiktionnaire
    -0.69
    RenderAtEndOf
    -0.66
    "]="
    -0.62
    ]+=
    -0.61
    UrlResolution
    -0.61
    ]='
    -0.58
    ]="
    -0.57
     صوتيه
    -0.56
    addCriterion
    -0.56
    ]<<"
    -0.55
    POSITIVE LOGITS
     ==
    1.42
     !=
    0.84
    ==
    0.76
    ==(
    0.52
    ()==
    0.51
     发表于
    0.49
    ցված
    0.49
    matchCondition
    0.47
     alkoh
    0.46
    ÔNG
    0.46
    Activations Density 0.095%

    No Known Activations