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. 14-GEMMASCOPE-RES-16K
    6. 13204
    Prev
    Next
    INDEX
    Explanations

    references to raw materials or data in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Walkover
    -0.83
    tvguidetime
    -0.83
    ngdoc
    -0.78
     <=",
    -0.76
     Eisenhower
    -0.74
     Merritt
    -0.73
    Kenn
    -0.72
     Tobi
    -0.70
    omitempty
    -0.69
     Kenn
    -0.68
    POSITIVE LOGITS
     Raw
    1.50
    Raw
    1.33
     raw
    1.31
     RAW
    1.19
    RAW
    1.10
    getRaw
    1.09
    rawData
    0.99
    raw
    0.97
    RawData
    0.96
     cruda
    0.87
    Activations Density 0.110%

    No Known Activations