© 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. 40-GEMMASCOPE-RES-16K
    6. 6229
    Prev
    Next
    INDEX
    Explanations

    terms related to statistical or mathematical descriptions in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.50
    lüğ
    -0.49
    
    -0.47
     архивлан
    -0.46
     myš
    -0.46
     pouvoit
    -0.45
     kişinin
    -0.44
     jorden
    -0.43
     namanya
    -0.42
     iliş
    -0.41
    POSITIVE LOGITS
     vicinity
    0.85
     neighbourhood
    0.73
     neighborhood
    0.71
     region
    0.63
    vic
    0.59
     interior
    0.56
    neighborhood
    0.54
     studied
    0.52
     investigated
    0.52
     vic
    0.52
    Activations Density 2.348%

    No Known Activations