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. 11000
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals and their familial connections

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

    Last names starting with prefixes

    np_acts-logits-general · gemini-2.0-flash

    people's 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
     Diſ
    -0.95
     Perſ
    -0.91
     Reſ
    -0.88
     Houſe
    -0.88
     Conſ
    -0.86
     Anſ
    -0.84
     Inſ
    -0.81
     abſ
    -0.81
     Beſ
    -0.78
     uſ
    -0.77
    POSITIVE LOGITS
    ✨:
    0.73
     Smith
    0.73
     De
    0.70
     Johnson
    0.67
     Mc
    0.66
     White
    0.66
     Green
    0.65
     O
    0.65
     Le
    0.64
     Brown
    0.63
    Activations Density 0.781%

    No Known Activations