Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 4624
    Prev
    Next
    INDEX
    Explanations

    phrases involving hypothetical scenarios or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows a comma or code-related punctuation

    np_acts-logits-general · gemini-2.0-flash

    units would

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,
    -0.55
    ord
    -0.54
     itself
    -0.52
     himself
    -0.51
     and
    -0.49
    ets
    -0.48
    ше
    -0.47
     Then
    -0.46
    oud
    -0.45
     (
    -0.43
    POSITIVE LOGITS
     AssemblyCulture
    1.14
    StructEnd
    0.97
    Vidite
    0.94
     ISNI
    0.83
    ValueStyle
    0.80
    FunctionFlags
    0.80
    ArrowToggle
    0.78
    UserScript
    0.77
    RegressionTest
    0.76
    msgTypes
    0.76
    Activations Density 0.061%

    No Known Activations