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. 8692
    Prev
    Next
    INDEX
    Explanations

    relationships and connections between characters or individuals

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

    Close relationships or exchanges

    np_acts-logits-general · gemini-2.0-flash

    close friendship discussions

    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
    躇
    -0.59
    aggreg
    -0.58
     subcontractors
    -0.57
    migrationBuilder
    -0.56
    ագրություններ
    -0.56
    örg
    -0.55
     ję
    -0.55
    SequentialGroup
    -0.55
    orr
    -0.55
     فريبيس
    -0.54
    POSITIVE LOGITS
     mutual
    1.11
    mutual
    0.94
    Mutual
    0.86
     friendship
    0.86
     exchanging
    0.81
     chemistry
    0.78
     Mutual
    0.78
     mutually
    0.76
     bond
    0.74
     shared
    0.73
    Activations Density 0.270%

    No Known Activations