© 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. 105663
    Prev
    Next
    INDEX
    Explanations

    recurring expressions of personal statements or opinions

    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
    valbard
    -0.43
     fec
    -0.39
    ItemStack
    -0.37
    gulp
    -0.34
    DllImport
    -0.34
     Melvin
    -0.34
    éto
    -0.33
    Desktop
    -0.33
    fee
    -0.33
    crollView
    -0.33
    POSITIVE LOGITS
    AndEndTag
    0.73
    点此举报
    0.61
    PreferredItem
    0.60
     utafitiHapana
    0.59
    AddHtmlAttribute
    0.55
    #+#
    0.54
     disambiguazione
    0.54
    Personendaten
    0.53
    évaluateur
    0.53
    ंदीखरीदारी
    0.52
    Activations Density 0.018%

    No Known Activations