© 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
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 5263
    Prev
    Next
    INDEX
    Explanations

    phrases expressing preference or desire

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

    phrases expressing desire or intent, particularly those using "I would like to".

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    -0.48
    <bos>
    -0.45
    بوابة
    -0.42
     endwhile
    -0.42
     deadly
    -0.41
     bandages
    -0.41
    Bảo
    -0.40
     Bayou
    -0.40
     barriers
    -0.39
    constructor
    -0.39
    POSITIVE LOGITS
     gustaría
    0.64
     InputDecoration
    0.62
    omitempty
    0.61
     informée
    0.60
    Dislikes
    0.59
     Liked
    0.58
    addGap
    0.57
     liked
    0.57
     LIK
    0.55
    Liked
    0.54
    Activations Density 0.039%

    No Known Activations