Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 14886
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and operations within code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/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.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     yyl
    -0.38
     /\.
    -0.37
    ParallelGroup
    -0.37
     stringBy
    -0.37
     invokevirtual
    -0.36
    /**
    -0.36
    SourceChecksum
    -0.35
     ffilmiau
    -0.35
    retudo
    -0.35
    ://$
    -0.35
    POSITIVE LOGITS
    ttemberg
    0.69
     reset
    0.59
     Explo
    0.55
     resets
    0.52
    reset
    0.51
     explode
    0.50
     resetting
    0.49
     exploded
    0.48
    重置
    0.47
    Reset
    0.47
    Activations Density 0.146%

    No Known Activations