© 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. 12-GEMMASCOPE-RES-16K
    11. 10680
    Prev
    Next
    INDEX
    Explanations

    conditional statements and questions about verification or assumptions

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

    clauses that express conditions or uncertainty (embedded yes/no questions and “if/whether” constructions)

    oai_token-act-pair · gpt-5Triggered by @areeb0102

    introducers of conditional clauses.

    oai_token-act-pair · deepseek-r1Triggered by @areeb0102

    conditional statements or questions introducing hypothetical scenarios and expressions of uncertainty.

    oai_token-act-pair · claude-4-5-haikuTriggered by @areeb0102
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    談社
    -0.77
     Daven
    -0.69
     kasarigan
    -0.65
     greateſt
    -0.64
    odeon
    -0.61
    HandlerContext
    -0.61
     hapa
    -0.61
     MacGregor
    -0.60
    most
    -0.60
    gaze
    -0.59
    POSITIVE LOGITS
     whether
    1.08
     WHETHER
    0.97
    whether
    0.89
     Whether
    0.84
     any
    0.79
     apakah
    0.77
    Whether
    0.77
    是否
    0.75
    是不是
    0.72
     是否
    0.71
    Activations Density 0.283%

    No Known Activations