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. 4-GEMMASCOPE-RES-16K
    6. 798
    Prev
    Next
    INDEX
    Explanations

    structured data or elements related to data management protocols

    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
    "}}
    -0.87
    RegressionTest
    -0.84
    errHandler
    -0.82
    '}}
    -0.74
    SequentialGroup
    -0.74
    endwhile
    -0.74
    ViewImports
    -0.72
     ExecuteAsync
    -0.72
    ⓧ
    -0.72
    ("}\
    -0.68
    POSITIVE LOGITS
    |
    1.67
    ||
    0.89
     |
    0.86
    |||
    0.77
    |,
    0.68
    |*
    0.66
    |"
    0.65
    |[
    0.64
    |+
    0.63
     $|
    0.59
    Activations Density 0.019%

    No Known Activations