© 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. 8261
    Prev
    Next
    INDEX
    Explanations

    references to specific materials and their properties

    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
    ThroughAttribute
    -0.90
    findpost
    -0.77
    WithIOException
    -0.74
    protoimpl
    -0.74
    ValueStyle
    -0.64
     adipis
    -0.60
     AspNetCore
    -0.59
    ReusableCell
    -0.58
     незавершена
    -0.57
    AddHtmlAttribute
    -0.56
    POSITIVE LOGITS
     wood
    1.81
    wood
    1.48
     Wood
    1.48
    Wood
    1.43
     wooden
    1.42
    WOOD
    1.35
     WOOD
    1.34
     timber
    1.29
     plywood
    1.23
    wooden
    1.23
    Activations Density 0.136%

    No Known Activations