© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 13394
    Prev
    Next
    INDEX
    Explanations

    references to various types of data entries or inputs related to accounts and verification processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     purpoſe
    -0.84
    存于互联网档案馆
    -0.83
     ſeveral
    -0.80
     stiefel
    -0.79
     cauſe
    -0.78
     ſever
    -0.78
     Majefty
    -0.77
     reaſon
    -0.77
     ſta
    -0.76
     poffible
    -0.76
    POSITIVE LOGITS
    JsonHelper
    0.65
    -------------</
    0.61
    )')
    0.61
    hagen
    0.61
    ongan
    0.60
    )))))
    0.58
    ))))
    0.56
    AGED
    0.56
     of
    0.56
    disposing
    0.56
    Activations Density 0.011%

    No Known Activations