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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 34-GEMMASCOPE-RES-16K
    6. 10985
    Prev
    Next
    INDEX
    Explanations

    specific product descriptions and their associated features or specifications

    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
     vectoriales
    -0.52
     oficinas
    -0.46
     virtuales
    -0.39
     hjär
    -0.38
     femininas
    -0.38
     zahrani
    -0.37
     exportaciones
    -0.37
     actualidad
    -0.36
     nowoczes
    -0.36
     volantes
    -0.36
    POSITIVE LOGITS
     kit
    0.77
     kits
    0.75
     pads
    0.73
     tubes
    0.69
     pods
    0.67
     proofs
    0.66
     rods
    0.65
     plates
    0.64
     boxes
    0.64
     cubes
    0.64
    Activations Density 0.757%

    No Known Activations