© 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. 15-GEMMASCOPE-RES-16K
    11. 3957
    Prev
    Next
    INDEX
    Explanations

    connections related to claims of legality and relevance 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 @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cydow
    -0.64
    PostExecute
    -0.60
    WebElementEntity
    -0.60
     consultato
    -0.53
     velocidades
    -0.50
    sivamente
    -0.49
    RepeatedField
    -0.49
    енча
    -0.48
    AYSIA
    -0.47
    لينا
    -0.46
    POSITIVE LOGITS
     relevance
    0.84
     relates
    0.76
     relate
    0.75
     relevan
    0.75
     relevant
    0.73
     related
    0.72
     connects
    0.69
     connection
    0.66
    Relevance
    0.66
     Relevance
    0.65
    Activations Density 0.354%

    No Known Activations