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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 9954
    Prev
    Next
    INDEX
    Explanations

    technical specifications and performance metrics of vehicles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyTitle
    -0.56
    \{\\
    -0.52
     Antenna
    -0.48
    writeField
    -0.48
     Sted
    -0.44
    mitteilung
    -0.44
    postsleuth
    -0.43
    шал
    -0.43
    Antenna
    -0.42
    żdż
    -0.42
    POSITIVE LOGITS
     engine
    1.56
     engines
    1.47
     Engine
    1.24
    engine
    1.18
     ENGINE
    1.17
     Engines
    1.14
    engines
    1.10
    Engine
    1.05
    エンジン
    0.98
    引擎
    0.98
    Activations Density 0.228%

    No Known Activations