© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 13496
    Prev
    Next
    INDEX
    Explanations

    structured data represented by numerical values and relational expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AnchorStyles
    -0.55
     BoxDecoration
    -0.52
    เช่น
    -0.41
    onAttach
    -0.41
    BeginInit
    -0.40
     läh
    -0.38
     well
    -0.37
    lementation
    -0.36
     again
    -0.36
    ╔
    -0.35
    POSITIVE LOGITS
    BufferException
    0.80
    +#+
    0.79
     通販
    0.78
    NameInMap
    0.77
     jsPsych
    0.76
    ----</
    0.74
    ftagPool
    0.73
    
    0.71
    Чыганаклар
    0.71
    ylvan
    0.71
    Activations Density 1.126%

    No Known Activations