© 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. 39-GEMMASCOPE-RES-16K
    6. 3939
    Prev
    Next
    INDEX
    Explanations

    technical terms related to nuclear physics and particle interactions

    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
    UserDefaults
    -0.44
    complexType
    -0.41
    ']))
    
    -0.41
     Benoît
    -0.40
     purpure
    -0.40
     вікі
    -0.39
     Mehmet
    -0.38
    SBATCH
    -0.38
     Vertrags
    -0.37
    Pressed
    -0.37
    POSITIVE LOGITS
     showers
    0.60
     bre
    0.60
     gam
    0.59
     scattering
    0.59
     cascade
    0.58
     Brems
    0.58
     gamma
    0.57
     collision
    0.57
     cascades
    0.56
     decay
    0.55
    Activations Density 1.430%

    No Known Activations