© 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. 12-GEMMASCOPE-RES-16K
    6. 2693
    Prev
    Next
    INDEX
    Explanations

    references to people, especially those related to healthcare, family, historical figures, or in contexts of studies and anthologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    trero
    -0.46
    Ronaldo
    -0.44
    intéress
    -0.42
    onFocus
    -0.41
     fubject
    -0.41
     ſche
    -0.40
    Kamer
    -0.40
    stdlib
    -0.40
     preſent
    -0.40
    Date
    -0.40
    POSITIVE LOGITS
    
    0.63
    Искәрмәләр
    0.60
     jsPsych
    0.57
     Roch
    0.57
    𝟘
    0.54
     Cane
    0.53
     multer
    0.53
     Coarse
    0.53
     Nio
    0.53
     Vaux
    0.52
    Activations Density 2.590%

    No Known Activations