© 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-2-9B
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 7427
    Prev
    Next
    INDEX
    Explanations

    coding-related constructs such as function definitions, returns, and promise handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     SqlParameter
    -0.61
    RTEX
    -0.59
     BorderLayout
    -0.59
    BagConstraints
    -0.59
    ſelf
    -0.58
     SqlDbType
    -0.57
    FontOfSize
    -0.55
    PullParser
    -0.55
     awakeFromNib
    -0.55
     StringTokenizer
    -0.53
    POSITIVE LOGITS
     perform
    0.39
     调用
    0.38
    invoke
    0.36
     انجام
    0.36
    CALL
    0.36
     gerçekleşti
    0.35
    みんなで
    0.35
     call
    0.35
     run
    0.35
    Await
    0.34
    Activations Density 0.400%

    No Known Activations