© 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. 13677
    Prev
    Next
    INDEX
    Explanations

    phrases related to selecting or retrieving items

    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
     CURIAM
    -0.92
    virons
    -0.85
    CORBA
    -0.84
    انتهای
    -0.79
    Cyfeiriadau
    -0.78
     contextLoads
    -0.78
    Abp
    -0.78
     للمعارف
    -0.76
    usitis
    -0.73
    httphttps
    -0.73
    POSITIVE LOGITS
     PICK
    1.77
     pick
    1.77
    Pick
    1.64
    pick
    1.62
     Pick
    1.59
     Picks
    1.57
     pickup
    1.54
    PICK
    1.53
     picks
    1.53
     picked
    1.53
    Activations Density 0.053%

    No Known Activations