© 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. 2777
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notation commonly used in formal equations and expressions

    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
    BibitemShut
    -0.76
     }}$}
    -0.75
    ✨:
    -0.68
    )");
    -0.67
    citenamefont
    -0.66
     itſelf
    -0.65
    "])
    -0.64
    RAINT
    -0.64
     doubtnut
    -0.63
     iſt
    -0.62
    POSITIVE LOGITS
     ExecuteAsync
    0.84
    IsContent
    0.72
     <=",
    0.70
    principalColumn
    0.70
    oredCriteria
    0.66
    imageshack
    0.63
    ThroughAttribute
    0.63
    peño
    0.61
    Carriera
    0.58
    StandardCharsets
    0.58
    Activations Density 4.928%

    No Known Activations