Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 13905
    Prev
    Next
    INDEX
    Explanations

    concepts related to meaning, success, faith, and emotional expression

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

    preceding "ful," "fully" or "fulness"

    np_acts-logits-general · gemini-2.0-flash

    full meaning, faithfulness, fruitfulness

    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
    OGND
    -0.92
    StoreMessageInfo
    -0.86
     صوتيه
    -0.83
    PerformLayout
    -0.83
    homonymie
    -0.81
     ProtoMessage
    -0.77
    帖最后由
    -0.75
    EndInit
    -0.75
     Lightboxes
    -0.75
     חיצוניים
    -0.74
    POSITIVE LOGITS
    full
    2.73
    fully
    2.66
    ful
    2.65
    fulness
    2.57
    FUL
    2.39
    FULL
    2.16
     full
    2.01
    Full
    1.94
    FULLY
    1.90
     Full
    1.80
    Activations Density 0.184%

    No Known Activations