© 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 - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 15916
    Prev
    Next
    INDEX
    Explanations

    references to investigations or reports involving police and governmental oversight

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegressionTest
    -0.48
     capot
    -0.43
     дописавши
    -0.41
    rungsseite
    -0.40
    ReusableCell
    -0.39
    styleType
    -0.36
     chers
    -0.36
     للاسماء
    -0.36
     appreciated
    -0.35
    awtextra
    -0.35
    POSITIVE LOGITS
     Inquiry
    0.75
     inquiry
    0.74
    Inquiry
    0.64
    QUIRY
    0.60
     enquiry
    0.59
    inquiry
    0.58
     CURIAM
    0.57
     Enquiry
    0.56
    kheim
    0.49
     inquiries
    0.47
    Activations Density 0.423%

    No Known Activations