© 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. 11-GEMMASCOPE-RES-16K
    11. 6696
    Prev
    Next
    INDEX
    Explanations

    indicators of system error messages and signals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    -0.65
     
    -0.64
    -
    -0.61
     or
    -0.60
     “
    -0.60
     X
    -0.55
    </i>
    -0.55
     Miss
    -0.55
     in
    -0.54
    ’
    -0.54
    POSITIVE LOGITS
     myſelf
    1.34
     itſelf
    1.31
    tagHelperRunner
    1.23
     defaultstate
    1.20
    OGND
    1.19
    +#+
    1.18
     تضيفلها
    1.16
     pleaſure
    1.15
    RenderAtEndOf
    1.12
    ⓧ
    1.11
    Activations Density 0.191%

    No Known Activations