© 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. 4-GEMMASCOPE-RES-16K
    11. 427
    Prev
    Next
    INDEX
    Explanations

    references to raw data or materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <=",
    -0.95
    ніципа
    -0.87
    ngdoc
    -0.82
    matchCondition
    -0.80
    SpringBootTest
    -0.77
    )))
    -0.76
    Portály
    -0.75
     continuant
    -0.73
    tvguidetime
    -0.73
     AssemblyVersion
    -0.72
    POSITIVE LOGITS
     Raw
    2.87
     raw
    2.80
    Raw
    2.69
    raw
    2.47
     RAW
    2.47
    RAW
    2.23
    getRaw
    1.63
    RawData
    1.61
    rawData
    1.56
     cruda
    1.20
    Activations Density 0.056%

    No Known Activations