© 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. 8-GEMMASCOPE-RES-16K
    6. 4894
    Prev
    Next
    INDEX
    Explanations

    specific characters or symbols used in markup and code formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Biôgrafia
    -0.70
    Personensuche
    -0.67
    WithIOException
    -0.60
    发表于
    -0.60
     Ghosh
    -0.58
    Personendaten
    -0.57
     Steele
    -0.55
     Ayers
    -0.55
    principalColumn
    -0.53
    klärt
    -0.53
    POSITIVE LOGITS
    ViewImports
    0.82
     BorderSide
    0.71
    }")
    
    0.67
    baomidou
    0.64
    VersionUID
    0.64
     kuten
    0.58
     kuin
    0.58
    antaranya
    0.57
    __':
    
    0.57
    __":
    
    0.57
    Activations Density 0.413%

    No Known Activations