© 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. 13637
    Prev
    Next
    INDEX
    Explanations

    numeric representations, particularly dates and identifiers

    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
     itſelf
    -1.41
     myſelf
    -1.38
     iſt
    -1.26
     purpoſe
    -1.24
     ſever
    -1.21
    ArrowToggle
    -1.19
     greateſt
    -1.14
     Reſ
    -1.14
     ―――――
    -1.14
    featureID
    -1.13
    POSITIVE LOGITS
     
    0.90
    ↵
    0.66
     I
    0.65
    </b>
    0.65
    </h2>
    0.62
      
    0.62
    1
    0.60
    ↵↵
    0.59
     (
    0.59
     P
    0.59
    Activations Density 0.437%

    No Known Activations