© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 8964
    Prev
    Next
    INDEX
    Explanations

    mentions of personal activities and experiences

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

    math or computers

    np_acts-logits-general · gemini-2.0-flash

    adventure, hiking, expeditions

    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
    NOPQRST
    -0.63
     decorativas
    -0.62
    EditorBrowsable
    -0.61
    MigrationBuilder
    -0.59
     kasarigan
    -0.59
     Eurovision
    -0.59
     industriale
    -0.58
    ollectionView
    -0.57
     decorativa
    -0.56
    MENAFN
    -0.56
    POSITIVE LOGITS
     adventure
    1.18
     hiking
    1.11
     wilderness
    1.05
     expedition
    1.03
     hike
    1.03
     adventures
    1.03
     trekking
    1.02
    adventure
    1.02
    Adventure
    1.02
     expeditions
    1.01
    Activations Density 0.165%

    No Known Activations