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. 20-GEMMASCOPE-RES-16K
    6. 969
    Prev
    Next
    INDEX
    Explanations

    contact information and URLs for various services and resources

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

    Email addresses and domains

    np_acts-logits-general · gemini-2.0-flash

    email domains

    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
     متعلقه
    -0.54
    RegressionTest
    -0.53
    AccessorTable
    -0.53
    却
    -0.53
     Nar
    -0.51
    ffl
    -0.49
    tagHelperRunner
    -0.49
    AndroidJUnit
    -0.48
    parseFrom
    -0.48
    ois
    -0.47
    POSITIVE LOGITS
     >=",
    0.70
    makeConstraints
    0.65
     <<<<<<<<<<<<<<
    0.62
    Chham
    0.58
    VersionUID
    0.57
    Noted
    0.55
    ineno
    0.54
     Wikimedijinoj
    0.53
    TagMode
    0.52
    jalá
    0.52
    Activations Density 0.099%

    No Known Activations