© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 6673
    Prev
    Next
    INDEX
    Explanations

    comparative and superlative adverbs

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

    preceding adjectives or adverbs

    np_acts-logits-general · gemini-2.0-flash

    rather followed by an adjective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -0.34
     conscientes
    -0.34
    プリング
    -0.33
     kimse
    -0.33
     consciente
    -0.33
    G
    -0.32
    foglal
    -0.32
     ]];
    -0.31
    B
    -0.31
    yarnpkg
    -0.31
    POSITIVE LOGITS
     robust
    0.62
     extremely
    0.61
    脚注の使い方
    0.59
     slaps
    0.58
     highly
    0.58
     versatile
    0.57
     incredibly
    0.57
     glamorous
    0.56
     colourful
    0.56
    یرات
    0.54
    Activations Density 0.406%

    No Known Activations