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. 11590
    Prev
    Next
    INDEX
    Explanations

    code elements related to functional programming and component structure in JavaScript/React

    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
    saraba
    -0.48
    发表于
    -0.47
     AssemblyTitle
    -0.46
     Roskov
    -0.44
    SequentialGroup
    -0.42
    rrggbb
    -0.41
    /*
    -0.41
     دیکھیے
    -0.40
    astéro
    -0.40
     kohdetta
    -0.40
    POSITIVE LOGITS
    handle
    0.80
     handle
    0.77
     Handle
    0.62
    Handle
    0.62
    useEffect
    0.60
     handles
    0.59
     HANDLE
    0.58
     handling
    0.57
    },[
    0.57
    dispatch
    0.57
    Activations Density 0.057%

    No Known Activations