© 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. 7769
    Prev
    Next
    INDEX
    Explanations

    terminology related to frequency and prevalence in health contexts

    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
    基本的に
    -0.38
    writerow
    -0.35
     eigentlich
    -0.32
     GenerationType
    -0.31
    كويكب
    -0.31
    EClass
    -0.31
    IsNullOrEmpty
    -0.31
     básicamente
    -0.30
    uação
    -0.29
    imize
    -0.29
    POSITIVE LOGITS
     often
    2.25
     frequently
    1.95
    often
    1.81
    Often
    1.80
     Often
    1.77
     часто
    1.72
     souvent
    1.68
    frequently
    1.66
     spesso
    1.64
     Frequently
    1.63
    Activations Density 0.460%

    No Known Activations