© 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. 14255
    Prev
    Next
    INDEX
    Explanations

    code and configuration-related terms and structures, particularly in programming or scripting contexts

    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
     Efq
    -0.90
    SourceChecksum
    -0.88
     pleaſure
    -0.87
     Monfieur
    -0.85
     purpoſe
    -0.85
     houſe
    -0.83
     Theſe
    -0.77
     whoſe
    -0.76
     Majefty
    -0.72
     juſ
    -0.72
    POSITIVE LOGITS
     add
    0.58
     thêm
    0.50
     added
    0.48
     extra
    0.46
     additional
    0.45
    add
    0.44
     tambahan
    0.44
    polic
    0.43
    WithMany
    0.43
    addAttribute
    0.42
    Activations Density 0.486%

    No Known Activations