© 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. 25-GEMMASCOPE-RES-16K
    11. 1091
    Prev
    Next
    INDEX
    Explanations

    phrases associated with specific scientific measurements and concentrations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     épaules
    -0.67
    ArgsConstructor
    -0.65
     utafitiHapana
    -0.64
    WebElementEntity
    -0.62
     distanza
    -0.57
    TagMode
    -0.56
    Apps
    -0.55
    IntoConstraints
    -0.55
    Atoms
    -0.55
    ⓧ
    -0.55
    POSITIVE LOGITS
     values
    1.45
     rates
    1.18
     speeds
    1.18
     amounts
    1.18
     prices
    1.17
    values
    1.14
     sizes
    1.12
     temperatures
    1.10
     lengths
    1.08
     thicknesses
    1.08
    Activations Density 1.998%

    No Known Activations