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. 39-GEMMASCOPE-RES-16K
    6. 893
    Prev
    Next
    INDEX
    Explanations

    phrases indicating various methods or tools used in communication and collaboration

    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
    Autoritní
    -0.77
    bootstrapcdn
    -0.73
     betweenstory
    -0.67
    
    -0.66
     cherchés
    -0.64
    Personendaten
    -0.63
     informée
    -0.62
     برانيه
    -0.61
     HasFactory
    -0.60
    CloseOperation
    -0.59
    POSITIVE LOGITS
     etc
    1.23
     even
    1.20
     lastly
    1.12
     finally
    1.09
     vieles
    1.07
     persino
    1.06
     sogar
    1.03
     ultimately
    1.02
    etc
    1.01
     даже
    0.99
    Activations Density 0.524%

    No Known Activations