© 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. 11-GEMMASCOPE-RES-16K
    11. 12840
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "raw" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    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
    -0.90
     épis
    -0.87
     <=",
    -0.85
    SBATCH
    -0.85
     дописавши
    -0.84
    RegistryLite
    -0.84
     comigo
    -0.81
    ///</
    -0.79
     يتيمه
    -0.79
     Accord
    -0.79
    POSITIVE LOGITS
     Raw
    1.78
     raw
    1.63
    Raw
    1.63
     RAW
    1.50
    RAW
    1.40
    raw
    1.37
    getRaw
    1.26
    RawData
    1.22
    rawData
    1.19
     cruda
    0.99
    Activations Density 0.078%

    No Known Activations