© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105706
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, specifically the period

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    ⓧ
    -0.58
     juſ
    -0.52
     ſch
    -0.51
    balleur
    -0.49
     deſt
    -0.49
     houſe
    -0.48
     pleaſure
    -0.48
    IBLIO
    -0.47
     cæ
    -0.47
     avoient
    -0.46
    POSITIVE LOGITS
    Portail
    0.61
    Portale
    0.57
     विश्वसनीयता
    0.56
     تضيفلها
    0.49
    بوابة
    0.48
     snippetHide
    0.44
    󠁢
    0.41
     extensive
    0.41
     sickening
    0.40
     للمعارف
    0.40
    Activations Density 0.000%

    No Known Activations