© 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. 24-GEMMASCOPE-RES-16K
    11. 5616
    Prev
    Next
    INDEX
    Explanations

    function calls and console logging commands in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code snippets or beginning of sentences

    np_acts-logits-general · gemini-2.0-flash

    Is there questions, pattern invention

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -0.62
    ftagPool
    -0.54
     Houſe
    -0.50
    eraard
    -0.50
     saites
    -0.49
     uſe
    -0.49
     ſte
    -0.47
     ſur
    -0.47
     iſt
    -0.47
    ſelf
    -0.47
    POSITIVE LOGITS
    
    0.42
    ValueStyle
    0.40
     scratch
    0.39
     Circumstances
    0.39
    PMailer
    0.39
    LOADED
    0.38
     loaded
    0.38
     checks
    0.38
     slippery
    0.37
    ht
    0.36
    Activations Density 0.106%

    No Known Activations