Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 7948
    Prev
    Next
    INDEX
    Explanations

    specific references to conditions and characteristics related to legal liability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Walkover
    -0.48
     uLocal
    -0.46
     vérit
    -0.45
    InSection
    -0.45
     vœux
    -0.44
    Tikang
    -0.43
     âmes
    -0.43
     boî
    -0.42
    Etimo
    -0.41
    colgroup
    -0.40
    POSITIVE LOGITS
     các
    0.80
     tubes
    0.61
     channels
    0.61
     lines
    0.60
     outlets
    0.59
     planes
    0.59
     Các
    0.58
     parties
    0.56
     batteries
    0.56
     shops
    0.56
    Activations Density 1.533%

    No Known Activations