© 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. 1-GEMMASCOPE-RES-16K
    11. 6765
    Prev
    Next
    INDEX
    Explanations

    phrases and words associated with the concept of "returning" or "bringing back."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    featureID
    -0.80
    SequentialGroup
    -0.77
     auroit
    -0.70
    NamedQueries
    -0.69
    ArrowToggle
    -0.69
    脚注の使い方
    -0.69
     سكانية
    -0.68
    :✨
    -0.68
    ControllerAdvice
    -0.68
    ftagPool
    -0.68
    POSITIVE LOGITS
     Brought
    0.63
     brings
    0.63
    Bring
    0.60
     brought
    0.60
     Bring
    0.59
    brought
    0.53
     Brings
    0.52
     bring
    0.51
     BRING
    0.51
     Besøkt
    0.49
    Activations Density 0.110%

    No Known Activations