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. 13864
    Prev
    Next
    INDEX
    Explanations

    personal attributes and professional backgrounds of individuals

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

    "[Name] is/has/analyzes"

    np_acts-logits-general · gemini-2.0-flash

    loves and is passionate about

    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
     objected
    -0.56
    mişti
    -0.55
    actéristiques
    -0.53
    Exactly
    -0.53
    object
    -0.49
     aanzien
    -0.48
    гава
    -0.48
     célèbres
    -0.48
     Nobel
    -0.47
    famous
    -0.47
    POSITIVE LOGITS
     passions
    0.90
     passionate
    0.88
     loves
    0.87
     passion
    0.83
     apasion
    0.82
     apaixon
    0.80
    passion
    0.76
     passione
    0.75
     Leidenschaft
    0.75
     currently
    0.73
    Activations Density 0.207%

    No Known Activations