© 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 - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 38559
    Prev
    Next
    INDEX
    Explanations

    the start of statements or sections in various contexts

    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
    MessageTagHelper
    -1.06
     betweenstory
    -1.06
    EndContext
    -0.96
    posedge
    -0.95
     HasFactory
    -0.94
    ValueStyle
    -0.93
    fromnode
    -0.91
     بيها
    -0.89
    AddTagHelper
    -0.88
     doubtnut
    -0.88
    POSITIVE LOGITS
    LookAnd
    0.44
    ']=='
    0.41
    "])
    0.40
    Active
    0.40
     window
    0.40
     mundial
    0.39
     B
    0.39
    bit
    0.38
    bar
    0.38
    high
    0.38
    Activations Density 0.039%

    No Known Activations