© 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. 2450
    Prev
    Next
    INDEX
    Explanations

    specific formatting cues and structural elements in the text

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

    Follows punctuation or specific symbols

    np_acts-logits-general · gemini-2.0-flash

    starts with A or Par

    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
    fontawesome
    -0.43
     (‘
    -0.43
     (\
    -0.40
    setTypeface
    -0.39
    ginfo
    -0.38
    zner
    -0.38
    cjonal
    -0.38
    (_
    -0.38
    flex
    -0.37
     Архивировано
    -0.37
    POSITIVE LOGITS
     autorytatywna
    1.09
    rungsseite
    0.99
    IndentedString
    0.94
     ModelExpression
    0.94
     дописавши
    0.93
     initComponents
    0.93
    SharedCtor
    0.91
     مرئيه
    0.90
    richTextPanel
    0.89
     Lightboxes
    0.88
    Activations Density 0.483%

    No Known Activations