Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 12381
    Prev
    Next
    INDEX
    Explanations

    references to figures and illustrations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TabIndex
    -0.67
    ThroughAttribute
    -0.65
    ---*/
    -0.64
    ⓧ
    -0.64
    ContentAsync
    -0.58
     defaultstate
    -0.57
    ($__
    -0.56
    LookAnd
    -0.55
    SourceChecksum
    -0.55
    +#+
    -0.54
    POSITIVE LOGITS
     diagram
    1.30
     diagrams
    1.24
     schematic
    1.07
     Diagram
    1.06
    diagram
    1.04
     Schematic
    1.03
    Diagram
    0.98
     DIAGRAM
    0.96
     Diagrams
    0.94
    Schematic
    0.93
    Activations Density 0.983%

    No Known Activations