© 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. 22-GEMMASCOPE-RES-16K
    11. 11310
    Prev
    Next
    INDEX
    Explanations

    questions directed at others, particularly inquiring if they have information or help regarding a specific topic

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

    Follows "anyone" or "you" and precedes question words

    np_acts-logits-general · gemini-2.0-flash

    anyone/you asking/wanting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.89
    rrggbb
    -0.84
    TypedDataSet
    -0.75
     expectation
    -0.66
    TintMode
    -0.65
    riwal
    -0.63
     tár
    -0.62
     mxArray
    -0.61
     Expectation
    -0.61
     ErrIntOverflow
    -0.61
    POSITIVE LOGITS
     mind
    0.81
     minded
    0.67
    mind
    0.61
    よろ
    0.60
     ever
    0.58
    Mind
    0.58
     care
    0.57
     Mind
    0.56
     Care
    0.53
     MIND
    0.50
    Activations Density 0.148%

    No Known Activations