© 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. 7-GEMMASCOPE-RES-16K
    11. 9728
    Prev
    Next
    INDEX
    Explanations

    instances of the term "raw" and related variations in context, indicating a focus on raw data or raw types

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.99
    ngdoc
    -0.97
     <=",
    -0.96
     AssemblyVersion
    -0.89
    StoryboardSegue
    -0.89
     épis
    -0.85
    appcompat
    -0.79
    ніципа
    -0.78
    routeProvider
    -0.77
    ///</
    -0.77
    POSITIVE LOGITS
     Raw
    2.04
     raw
    1.92
    Raw
    1.87
     RAW
    1.74
    raw
    1.69
    RAW
    1.62
    getRaw
    1.34
    RawData
    1.30
    rawData
    1.20
     cruda
    1.03
    Activations Density 0.043%

    No Known Activations