© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 15545
    Prev
    Next
    INDEX
    Explanations

    code structures and functions related to web server configurations

    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
    IContainer
    -0.60
    ↵↵
    -0.58
        
    -0.52
    MigrationBuilder
    -0.51
     initComponents
    -0.48
     Emits
    -0.45
      
    -0.45
    componentDid
    -0.44
    פון
    -0.43
    icam
    -0.42
    POSITIVE LOGITS
    spesies
    0.91
     CreateTagHelper
    0.79
     كومونز
    0.71
     odkazy
    0.69
    makeText
    0.66
    исленность
    0.64
    Brainz
    0.64
    VersionUID
    0.64
    TagMode
    0.64
    AnchorStyles
    0.63
    Activations Density 0.040%

    No Known Activations