© 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. 4-GEMMASCOPE-RES-16K
    11. 3622
    Prev
    Next
    INDEX
    Explanations

    specific code syntax elements or structures in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     énergé
    -0.48
     daarvan
    -0.44
     ugy
    -0.44
    soci
    -0.43
     nyata
    -0.42
     bū
    -0.42
    )}</
    -0.42
     cheio
    -0.41
     assust
    -0.41
     umana
    -0.40
    POSITIVE LOGITS
     ModelExpression
    1.02
    Datuak
    0.90
    ChildScrollView
    0.89
    GenerationType
    0.87
    ########.
    0.86
    MessageTagHelper
    0.82
    httphttps
    0.80
    sizeCache
    0.79
    skjaer
    0.78
    جغرافيا
    0.76
    Activations Density 0.077%

    No Known Activations