© 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. 11333
    Prev
    Next
    INDEX
    Explanations

    descriptive elements related to scenery and nature

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

    Distant or partially visible objects/landscapes

    np_acts-logits-general · gemini-2.0-flash

    distant objects and silhouettes

    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
    BagLayout
    -0.93
     estekak
    -0.87
    دانشنامهٔ
    -0.78
     muualla
    -0.73
    mybatisplus
    -0.73
    AddHtmlAttribute
    -0.73
    setVerticalGroup
    -0.73
     Мексичка
    -0.72
     мәкал
    -0.71
    complexType
    -0.70
    POSITIVE LOGITS
     silhouettes
    0.89
     silueta
    0.82
     silhouette
    0.81
     approaching
    0.80
     distant
    0.79
     ahead
    0.78
     visible
    0.72
     näky
    0.71
     horizon
    0.70
    distant
    0.69
    Activations Density 0.218%

    No Known Activations