© 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. 3676
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their usage in code or textual contexts

    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
    GraphicsUnit
    -0.85
     autorytatywna
    -0.83
     referenties
    -0.77
    Enllaces
    -0.74
    .*")]
    -0.70
     AppModule
    -0.65
    adaptiveStyles
    -0.64
    onHide
    -0.63
    Personensuche
    -0.62
     خارجية
    -0.62
    POSITIVE LOGITS
     يتيمه
    0.60
    chapper
    0.58
     '{@
    0.51
     compter
    0.50
    SourceChecksum
    0.50
    JspWriter
    0.49
     flyknit
    0.48
     AssemblyCulture
    0.47
    Pageable
    0.47
    Altri
    0.47
    Activations Density 0.084%

    No Known Activations