© 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. 21-GEMMASCOPE-RES-16K
    11. 6343
    Prev
    Next
    INDEX
    Explanations

    references to increases or changes in measurements or values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sols
    -0.54
    chluss
    -0.48
    各样的
    -0.46
     initComponents
    -0.45
    ar
    -0.45
    al
    -0.43
    ός
    -0.42
    sz
    -0.42
    AddRange
    -0.42
    Wirtschaft
    -0.41
    POSITIVE LOGITS
    AccessorTable
    0.91
    mybatisplus
    0.90
    UserScript
    0.89
    GraphicsUnit
    0.87
    +#+#
    0.82
     autorytatywna
    0.79
     nahilalakip
    0.77
    دانشنامهٔ
    0.76
    EndProject
    0.75
     transfieras
    0.74
    Activations Density 0.197%

    No Known Activations