© 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. 9472
    Prev
    Next
    INDEX
    Explanations

    instances of locations and actions related to crime scenes and legal procedures

    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
     estekak
    -0.66
    المشاركات
    -0.63
    httphttps
    -0.59
    KommentareTeilen
    -0.57
     iconLine
    -0.54
     Wicidata
    -0.54
    Хьажоргаш
    -0.54
     Италијани
    -0.53
    Havolalar
    -0.53
    Географиясе
    -0.53
    POSITIVE LOGITS
     to
    0.75
     for
    0.63
     để
    0.53
     untuk
    0.52
    เพื่อ
    0.51
     seeking
    0.50
     armed
    0.49
     carrying
    0.48
     upang
    0.47
     early
    0.45
    Activations Density 0.459%

    No Known Activations