© 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. 16-GEMMASCOPE-RES-16K
    11. 7644
    Prev
    Next
    INDEX
    Explanations

    statistical or programming constructs related to data access and manipulation

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

    Code, statistics, or math syntax

    np_acts-logits-general · gemini-2.0-flash

    code, math notation, UI elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NameInMap
    -0.60
     useDispatch
    -0.59
    いたり
    -0.58
     and
    -0.54
     transfieras
    -0.53
    RepeatedField
    -0.51
     @"/
    -0.50
    RTSN
    -0.50
     or
    -0.50
    ául
    -0.50
    POSITIVE LOGITS
     ویکی‌پدیای
    0.71
    uxxxx
    0.68
    yntaxException
    0.67
    دانشنامهٔ
    0.64
    TypedDataSet
    0.63
     Audiodateien
    0.58
    onViewCreated
    0.57
    лтемелер
    0.57
     numberOfRows
    0.56
    MemoryWarning
    0.55
    Activations Density 0.196%

    No Known Activations