© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 9254
    Prev
    Next
    INDEX
    Explanations

    punctuation symbols in the context of coding or programming languages

    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
    PageRoute
    -0.51
     pihak
    -0.46
    @
    -0.45
    <sup>
    -0.45
    ony
    -0.42
    cip
    -0.42
    pora
    -0.42
    <em>
    -0.42
    吊
    -0.41
    http
    -0.41
    POSITIVE LOGITS
    PasswordEncoder
    1.07
    DoubleQuotes
    0.93
     myſelf
    0.91
     Efq
    0.88
    RenderAtEndOf
    0.81
     itſelf
    0.80
    featureID
    0.80
    ]--;
    0.79
    cstring
    0.78
     Monfieur
    0.76
    Activations Density 0.018%

    No Known Activations