© 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 - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 14781
    Prev
    Next
    INDEX
    Explanations

    conditional statements and configurations in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IVEREF
    -0.75
    ViewFeatures
    -0.64
     AssemblyCulture
    -0.62
    makeConstraints
    -0.57
    OrNil
    -0.56
     مشين
    -0.56
    __':
    
    -0.55
    smithy
    -0.55
    RectangleBorder
    -0.51
    __":
    
    -0.51
    POSITIVE LOGITS
    Synonymes
    0.56
     vapore
    0.54
     adopt
    0.53
    PhysRev
    0.52
    ാല
    0.52
    脚注の使い方
    0.52
    ExecuteReader
    0.52
    ardes
    0.52
    opter
    0.51
    gie
    0.50
    Activations Density 0.062%

    No Known Activations