© 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. 6908
    Prev
    Next
    INDEX
    Explanations

    sections of the document that contain numerical data or codes

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

    Numbers indicating days of the month

    np_acts-logits-general · gemini-2.0-flash

    dates and years

    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
     CreateTagHelper
    -1.23
     nahilalakip
    -1.12
     autorytatywna
    -1.03
     propOrder
    -1.02
     חיצוניים
    -0.95
    ValueStyle
    -0.95
     defaultstate
    -0.90
     contextLoads
    -0.90
    mybatisplus
    -0.87
    igshid
    -0.86
    POSITIVE LOGITS
     
    0.87
    1
    0.62
    2
    0.62
    ↵
    0.52
     [
    0.52
    3
    0.51
     Le
    0.47
     Bre
    0.47
     Non
    0.46
    e
    0.44
    Activations Density 0.067%

    No Known Activations