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. 1-GEMMASCOPE-RES-16K
    6. 14948
    Prev
    Next
    INDEX
    Explanations

    terms related to electronic devices and technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.86
     ModelExpression
    -0.83
    DataURL
    -0.76
     PyLong
    -0.75
    "}\
    -0.66
    writeFieldEnd
    -0.65
    expandindo
    -0.64
     mxArray
    -0.64
     quarries
    -0.63
     Permalink
    -0.61
    POSITIVE LOGITS
     ghost
    0.91
     electronic
    0.84
    Electronic
    0.83
    ghost
    0.83
     Electronic
    0.81
    Ghost
    0.79
    Sou
    0.76
     Ghost
    0.75
     sou
    0.73
     ghosts
    0.68
    Activations Density 0.065%

    No Known Activations