© 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. 3725
    Prev
    Next
    INDEX
    Explanations

    elements associated with images and avatars in a code context

    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
    DispatchToProps
    -0.77
     rootReducer
    -0.69
    setupUi
    -0.66
    évaluateur
    -0.66
    TabIndex
    -0.66
    cshtml
    -0.64
    IntentFilter
    -0.62
     nahilalakip
    -0.60
    Kaynakça
    -0.60
    JvmStatic
    -0.60
    POSITIVE LOGITS
    ImageField
    0.79
    avatar
    0.76
    setImage
    0.69
    NOPQRST
    0.67
    Avatar
    0.64
     setImage
    0.64
     ảnh
    0.64
     avatar
    0.63
    IMG
    0.63
    ImageIcon
    0.62
    Activations Density 0.264%

    No Known Activations