© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 14066
    Prev
    Next
    INDEX
    Explanations

    special formatting patterns or markers in scientific documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     N
    -0.65
    bParam
    -0.64
     L
    -0.64
     Vin
    -0.64
     T
    -0.63
     }{\
    -0.62
    fillType
    -0.62
     Fra
    -0.62
    RuleContext
    -0.62
    脚注の使い方
    -0.61
    POSITIVE LOGITS
     SSS
    1.15
     Shakspeare
    1.10
    AAA
    1.07
    xxx
    0.99
     lili
    0.99
    XXX
    0.99
     AAA
    0.99
     fff
    0.99
    >>>>>
    0.98
    >>>
    0.96
    Activations Density 0.341%

    No Known Activations