© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 11179
    Prev
    Next
    INDEX
    Explanations

    references to scientific measurements and calculations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.69
     Мексичка
    -0.61
     faſt
    -0.55
     ſal
    -0.53
     snippetHide
    -0.51
    Sucesor
    -0.46
     raiſ
    -0.45
     betweenstory
    -0.45
    étoit
    -0.45
    MessageTagHelper
    -0.45
    POSITIVE LOGITS
     SF
    1.59
     CF
    1.51
     PF
    1.50
     HF
    1.45
    SF
    1.45
     MF
    1.45
     BF
    1.42
     GF
    1.41
     sf
    1.39
     LF
    1.39
    Activations Density 0.773%

    No Known Activations