© 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. 6-GEMMASCOPE-RES-16K
    11. 656
    Prev
    Next
    INDEX
    Explanations

    HTML tags and related content within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defaultstate
    -1.15
    !*\
    -0.97
    AsUp
    -0.96
    TargetException
    -0.95
    TestingModule
    -0.93
    providedIn
    -0.91
     noqa
    -0.90
    cassert
    -0.85
    
    -0.85
    jfree
    -0.85
    POSITIVE LOGITS
    html
    2.17
     html
    2.04
    Html
    1.89
     Html
    1.88
     HTML
    1.79
    HTML
    1.70
    shtml
    1.17
    tml
    1.14
    htm
    1.01
    brtc
    0.73
    Activations Density 0.051%

    No Known Activations