© 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-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 10808
    Prev
    Next
    INDEX
    Explanations

    numerical values and their relationships or comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 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
    qrstuvwxyz
    -0.55
    __':
    
    -0.54
    ttemberg
    -0.54
    adə
    -0.52
    Kaieteur
    -0.51
    HasForeignKey
    -0.50
    </h1>
    -0.50
    :])
    -0.50
     CanadaChoose
    -0.49
     الحره
    -0.49
    POSITIVE LOGITS
     étoit
    0.68
     auroit
    0.62
     aveug
    0.61
     quæ
    0.61
     habet
    0.60
     sauvages
    0.59
     postale
    0.58
     térm
    0.57
     judicia
    0.56
     küpe
    0.55
    Activations Density 1.362%

    No Known Activations