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. 5787
    Prev
    Next
    INDEX
    Explanations

    email addresses and associated URLs

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

    before ".com" or similar TLDs

    np_acts-logits-general · gemini-2.0-flash

    company names

    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
    Personendaten
    -0.79
    LookAnd
    -0.76
    addCriterion
    -0.75
     виправивши
    -0.71
     AssemblyTitle
    -0.70
    PreferredItem
    -0.70
    ')")
    -0.68
    %");
    -0.66
    saraba
    -0.66
    IsMutable
    -0.66
    POSITIVE LOGITS
    com
    1.32
     com
    1.18
    Com
    0.99
     Com
    0.84
    COM
    0.83
     dot
    0.78
    net
    0.76
     org
    0.73
    .
    0.72
     net
    0.70
    Activations Density 0.223%

    No Known Activations