© 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. 20-GEMMASCOPE-RES-16K
    11. 7122
    Prev
    Next
    INDEX
    Explanations

    code-related terms and syntax, particularly those pertaining to threading and data retrieval structures

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

    "id" strings, often related to threads or UI elements

    np_acts-logits-general · gemini-2.0-flash

    variable or object id

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     виправивши
    -0.49
    insegna
    -0.47
     conjun
    -0.47
     ['./
    -0.46
    NonQuery
    -0.46
     wann
    -0.45
    writeFieldEnd
    -0.45
     plough
    -0.45
     Thế
    -0.44
     Bote
    -0.44
    POSITIVE LOGITS
     id
    2.30
     ID
    2.19
    id
    2.07
     Id
    2.04
    Id
    1.94
    ID
    1.93
     IDs
    1.79
     identification
    1.73
    getId
    1.69
     getId
    1.68
    Activations Density 0.177%

    No Known Activations