© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 331
    Prev
    Next
    INDEX
    Explanations

    references to panels or discussions related to group settings or assemblies

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

    "panel" followed by specific prepositions or nouns

    np_acts-logits-general · gemini-2.0-flash

    panel discussion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    حياتها
    -0.57
     pinulongan
    -0.56
    슷
    -0.55
    جغرافيا
    -0.55
    ostoma
    -0.53
    IZACIÓN
    -0.53
    ium
    -0.50
     تكبرها
    -0.50
    سكرية
    -0.49
    uminense
    -0.49
    POSITIVE LOGITS
     panels
    1.25
     Panels
    1.15
    panels
    1.13
     panel
    1.11
     Panel
    1.11
    Panels
    1.06
     PANEL
    1.05
    panel
    1.04
     Pane
    0.98
    PANEL
    0.98
    Activations Density 0.147%

    No Known Activations