© 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. 590
    Prev
    Next
    INDEX
    Explanations

    expressions of preference or affection

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

    Comes before opinions or preferences

    np_acts-logits-general · gemini-2.0-flash

    expressing liking

    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
     endwhile
    -0.49
    بوابة
    -0.48
    <bos>
    -0.47
     breathtaking
    -0.45
     devastating
    -0.45
     breakthroughs
    -0.43
     سكانية
    -0.42
     Burnham
    -0.42
    ^
    -0.41
    lastonbury
    -0.41
    POSITIVE LOGITS
    Dislikes
    0.67
     InputDecoration
    0.66
     liked
    0.64
    Liked
    0.61
     Liked
    0.60
    dislike
    0.59
    liked
    0.59
     Likes
    0.56
    Likes
    0.54
     gusta
    0.54
    Activations Density 0.064%

    No Known Activations