© 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. 10720
    Prev
    Next
    INDEX
    Explanations

    comparative phrases that emphasize similarity or importance

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

    "as" followed by an adjective or adverb

    np_acts-logits-general · gemini-2.0-flash

    comparative and descriptive "as"

    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
    TagMode
    -0.91
     referenties
    -0.75
    таратура
    -0.67
     StatefulWidget
    -0.63
    ंदीखरीदारी
    -0.60
     ElementRef
    -0.59
    centiles
    -0.58
     []),
    -0.56
    /***/
    -0.55
    rrggbb
    -0.55
    POSITIVE LOGITS
    存于互联网档案馆
    0.59
    __':
    0.58
     much
    0.55
     HasFactory
    0.55
     good
    0.54
     Patro
    0.54
     vain
    0.52
     Aso
    0.51
    enumi
    0.50
    WHEREAS
    0.50
    Activations Density 0.105%

    No Known Activations