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. 17-GEMMASCOPE-RES-16K
    6. 5762
    Prev
    Next
    INDEX
    Explanations

    relationships involving statistical measures or distributions in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onViewCreated
    -0.66
     linkovi
    -0.64
     BoxDecoration
    -0.63
     createSlice
    -0.62
    SequentialGroup
    -0.61
    onActivityResult
    -0.57
    portál
    -0.56
    __*/
    -0.56
     bParam
    -0.56
    extAlignment
    -0.56
    POSITIVE LOGITS
     increasing
    1.32
     Increasing
    1.29
    Increasing
    1.23
    increasing
    1.19
     increases
    1.17
     increase
    1.12
     decreasing
    0.98
    increases
    0.97
     Increase
    0.95
    increase
    0.95
    Activations Density 1.254%

    No Known Activations