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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 39-GEMMASCOPE-RES-16K
    11. 3311
    Prev
    Next
    INDEX
    Explanations

    elements and structures related to research funding and sourcing in academic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tables
    -0.67
     Targets
    -0.65
    Tren
    -0.65
    taps
    -0.64
    Thru
    -0.63
    trains
    -0.63
    Than
    -0.63
    Tun
    -0.62
    TRY
    -0.61
    Tries
    -0.61
    POSITIVE LOGITS
     տ
    0.45
     ט
    0.44
    afficheront
    0.40
     trock
    0.39
     toek
    0.39
    تقاوى
    0.39
    kkue
    0.39
    tagPool
    0.38
    tagHelperRunner
    0.37
    ofern
    0.37
    Activations Density 2.882%

    No Known Activations