© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 55631
    Prev
    Next
    INDEX
    Explanations

    words that signify exclusivity or uniqueness

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

    only followed by other words

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    ！”
    -0.40
    ！」
    -0.39
     ſtate
    -0.38
     myſelf
    -0.38
    IpAddress
    -0.38
     livestream
    -0.37
    !」
    -0.36
    、「
    -0.36
    ~”
    -0.35
    Personensuche
    -0.35
    POSITIVE LOGITS
     Administrativna
    0.91
     للمعارف
    0.82
    ỡng
    0.68
     ligiloj
    0.67
    पया
    0.66
     esternos
    0.61
     के
    0.61
    <_>
    0.59
    estinal
    0.59
     umane
    0.58
    Activations Density 0.008%

    No Known Activations