© 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. 17-GEMMASCOPE-RES-16K
    11. 13526
    Prev
    Next
    INDEX
    Explanations

    programming concepts related to handling data and processing user input

    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
    NotFoundError
    -0.48
     in
    -0.48
     berp
    -0.47
     itself
    -0.46
     “
    -0.45
     of
    -0.44
     ”
    -0.44
    wapV
    -0.43
     at
    -0.42
     es
    -0.42
    POSITIVE LOGITS
     purpoſe
    1.29
     Theſe
    1.23
    ſelves
    1.20
    ſelf
    1.18
     pleaſure
    1.16
     Monfieur
    1.14
     greateſt
    1.14
     myſelf
    1.12
     ſeveral
    1.11
     Anſ
    1.11
    Activations Density 0.591%

    No Known Activations