© 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. 8950
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to community interactions and social norms

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

    the word "at"

    np_acts-logits-general · gemini-2.0-flash

    at least

    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
    <sup>
    -0.49
     
    -0.49
     F
    -0.48
     isso
    -0.47
     Be
    -0.46
    openModal
    -0.45
     '
    -0.44
     Car
    -0.44
     E
    -0.43
    ↵↵
    -0.42
    POSITIVE LOGITS
    enumi
    0.87
    enderror
    0.79
     uſed
    0.75
    CloseOperation
    0.75
     henvisninger
    0.75
     purpoſe
    0.73
     ſmall
    0.72
    rrggbb
    0.71
    AutoresizingMask
    0.70
    ValueStyle
    0.70
    Activations Density 0.301%

    No Known Activations