© 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. 4-GEMMASCOPE-RES-16K
    11. 422
    Prev
    Next
    INDEX
    Explanations

    technical terminology and references related to programming, computer architecture, and floating-point units

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.80
    AndEndTag
    -0.77
     OMITBAD
    -0.73
    DeleteBehavior
    -0.73
     continúas
    -0.70
     فريبيس
    -0.69
     cherchés
    -0.67
    adaptiveStyles
    -0.66
     Exactos
    -0.65
    Sucesor
    -0.63
    POSITIVE LOGITS
     piemē
    0.48
     ساعد
    0.47
    くれて
    0.46
    unched
    0.45
    fæ
    0.45
    ValueStyle
    0.45
    ļu
    0.43
    แต่
    0.42
    like
    0.42
    Like
    0.42
    Activations Density 1.261%

    No Known Activations