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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15-GEMMASCOPE-RES-16K
    6. 1489
    Prev
    Next
    INDEX
    Explanations

    text related to file paths and system commands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    modb
    -0.61
     IRL
    -0.47
    extAlignment
    -0.47
    AnchorStyles
    -0.46
    öbb
    -0.45
     gql
    -0.43
    AxisAlignment
    -0.43
    GraphQL
    -0.42
    bitField
    -0.41
    tablename
    -0.41
    POSITIVE LOGITS
     installed
    0.84
     installation
    0.79
     installs
    0.79
     installing
    0.77
     versions
    0.76
     getVersion
    0.75
     install
    0.75
     compatibility
    0.73
     incompatibility
    0.73
    install
    0.72
    Activations Density 0.968%

    No Known Activations