© 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. 3-GEMMASCOPE-RES-16K
    11. 9881
    Prev
    Next
    INDEX
    Explanations

    terms related to retrieving or recovering data or information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.75
    tekend
    -0.68
     שוליים
    -0.66
     newState
    -0.66
     råd
    -0.62
    ARGS
    -0.61
     Consideration
    -0.59
    
    -0.58
     Masa
    -0.58
     Pardon
    -0.57
    POSITIVE LOGITS
     retrieve
    2.46
     retrieved
    2.27
     retrieval
    2.17
     Retrieval
    2.15
     Retrieve
    2.14
     retrieves
    2.13
     retrieving
    2.10
    Retrieve
    2.08
    Retrieval
    1.97
    retrieve
    1.94
    Activations Density 0.049%

    No Known Activations