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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 9-GEMMASCOPE-RES-16K
    6. 15339
    Prev
    Next
    INDEX
    Explanations

    references to raw or unprocessed materials and data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    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
    -0.91
     <=",
    -0.83
     épis
    -0.82
    dição
    -0.81
    ngdoc
    -0.79
    routeProvider
    -0.77
     comigo
    -0.76
    ///</
    -0.74
     Diener
    -0.74
    RegistryLite
    -0.74
    POSITIVE LOGITS
     Raw
    1.83
     raw
    1.70
    Raw
    1.69
     RAW
    1.60
    RAW
    1.49
    raw
    1.45
    getRaw
    1.23
    RawData
    1.22
    rawData
    1.19
     cruda
    1.04
    Activations Density 0.088%

    No Known Activations