© 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. 3961
    Prev
    Next
    INDEX
    Explanations

    names of individuals and family-related terms

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

    Tokens before names

    np_acts-logits-general · gemini-2.0-flash

    names followed by names

    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
     تضيفلها
    -1.04
    setVerticalGroup
    -0.99
     للمعارف
    -0.98
    AnchorStyles
    -0.94
    AndEndTag
    -0.94
    ReusableCell
    -0.92
    ScopeManager
    -0.87
    ImageContext
    -0.85
    abestanden
    -0.82
     Erişim
    -0.81
    POSITIVE LOGITS
    blå
    0.46
    ogaster
    0.41
     nhiêu
    0.40
     (
    0.39
     fehér
    0.39
     "
    0.37
    atus
    0.36
    meyen
    0.35
    ,
    0.35
    ie
    0.34
    Activations Density 0.070%

    No Known Activations