© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 9768
    Prev
    Next
    INDEX
    Explanations

    coding-related terms and characters associated with data formatting or encoding issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     complètes
    -0.73
    ReusableCell
    -0.73
    GOTREF
    -0.72
    DebuggerNonUser
    -0.66
    UnitTesting
    -0.63
    RUnlock
    -0.63
    WaitGroup
    -0.62
     élevées
    -0.62
    ModelSerializer
    -0.61
     présidenti
    -0.61
    POSITIVE LOGITS
     Unicode
    0.64
    Unicode
    0.59
     charset
    0.58
     unicode
    0.57
     emoji
    0.57
    charset
    0.56
    JIS
    0.56
    encoding
    0.54
    StandardCharsets
    0.54
    charCodeAt
    0.52
    Activations Density 0.527%

    No Known Activations