© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 27-GEMMASCOPE-RES-16K
    6. 10007
    Prev
    Next
    INDEX
    Explanations

    mentions of specific natural beings or characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    majánló
    -0.71
    cemment
    -0.66
    tagext
    -0.60
    ロウィン
    -0.60
     يتيمه
    -0.58
    ollectionView
    -0.58
     ujednoznacz
    -0.57
     hibernate
    -0.55
    anskje
    -0.54
     intptr
    -0.54
    POSITIVE LOGITS
     preis
    0.28
    ありません
    0.27
    되었습니다
    0.27
     terper
    0.26
    #
    0.26
     was
    0.26
     الأع
    0.26
     feest
    0.26
     constituted
    0.25
     feit
    0.25
    Activations Density 0.329%

    No Known Activations