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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 14684
    Prev
    Next
    INDEX
    Explanations

    comparative measurements and mathematical ratios

    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
     ExecuteAsync
    -0.71
     فريبيس
    -0.71
     AssemblyCompany
    -0.69
    دانشنامهٔ
    -0.69
     snippetHide
    -0.68
    enderror
    -0.68
    Personensuche
    -0.67
    Referencies
    -0.66
    GEBURTSDATUM
    -0.65
    invokeLater
    -0.65
    POSITIVE LOGITS
     margin
    0.51
     ganzen
    0.48
     signifikan
    0.47
     notches
    0.46
     notch
    0.46
     percentage
    0.45
     noticeable
    0.42
     increments
    0.41
     increment
    0.41
     factor
    0.40
    Activations Density 0.459%

    No Known Activations