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. 22-GEMMASCOPE-RES-16K
    6. 3431
    Prev
    Next
    INDEX
    Explanations

    connections between ideas or entities

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

    "and" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    listing and concluding items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Its
    -0.60
    lapsingToolbar
    -0.56
     Its
    -0.56
    AlterField
    -0.53
    woosh
    -0.52
     değildir
    -0.50
    WebElementEntity
    -0.49
    keyColumn
    -0.49
    nocześnie
    -0.49
    かつ
    -0.49
    POSITIVE LOGITS
     etc
    1.65
     persino
    1.46
     even
    1.40
    etc
    1.38
     sebagainya
    1.35
    Etc
    1.30
     lastly
    1.29
     finally
    1.25
     dergleichen
    1.23
     Etc
    1.23
    Activations Density 0.348%

    No Known Activations