© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 7834
    Prev
    Next
    INDEX
    Explanations

    terms related to academic institutions and research grants

    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
    ⓧ
    -0.43
     Hundreds
    -0.32
     détaillée
    -0.32
    ellemző
    -0.31
    pieler
    -0.31
     Peny
    -0.30
     Within
    -0.29
     Basic
    -0.29
     basic
    -0.29
    Within
    -0.29
    POSITIVE LOGITS
    cshtml
    0.59
    ArgsConstructor
    0.57
    ंदीखरीदारी
    0.56
    webElementXpaths
    0.56
    KommentareTeilen
    0.54
    
    0.52
    æus
    0.52
     utafitiHapana
    0.52
    -------
    0.51
     iconLine
    0.51
    Activations Density 1.024%

    No Known Activations