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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 31-GEMMASCOPE-RES-16K
    6. 16262
    Prev
    Next
    INDEX
    Explanations

    specific references to transportation-related entities and legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IsNotNull
    -0.40
     CanadaChoose
    -0.39
     cra
    -0.31
     Gegenteil
    -0.31
    dyr
    -0.30
    Życiorys
    -0.30
     though
    -0.29
     bow
    -0.29
     es
    -0.29
     bij
    -0.29
    POSITIVE LOGITS
    PerformLayout
    0.65
     U
    0.60
    ſelf
    0.58
     UO
    0.57
     UB
    0.57
     myſelf
    0.56
     '\\;'
    0.56
     UD
    0.56
    fjspx
    0.56
     UU
    0.53
    Activations Density 0.527%

    No Known Activations