© 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. 7-GEMMASCOPE-RES-16K
    11. 9866
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and logical statements related to mathematical proofs or arguments

    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
    writeFieldEnd
    -0.84
    GOTREF
    -0.83
    parsedMessage
    -0.74
     विश्वसनीयता
    -0.72
     itſelf
    -0.68
    OGND
    -0.68
    TintMode
    -0.67
     houſe
    -0.67
    ItemBackground
    -0.67
     Infór
    -0.67
    POSITIVE LOGITS
    Hozzáférés
    0.57
    ViewById
    0.46
     فريبيس
    0.40
    abı
    0.39
     становника
    0.38
    DataMember
    0.37
    defaultProps
    0.37
    diyesi
    0.36
    Implications
    0.35
     i
    0.34
    Activations Density 0.857%

    No Known Activations