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. 33-GEMMASCOPE-RES-16K
    6. 516
    Prev
    Next
    INDEX
    Explanations

    transitional phrases and expressions indicating progression or movement through a process

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     daardoor
    -0.65
     wcześ
    -0.64
     awalnya
    -0.60
     obecnie
    -0.58
     pertanto
    -0.58
     hierbei
    -0.58
     vooraf
    -0.58
     sengaja
    -0.57
     wcześniej
    -0.57
     därför
    -0.56
    POSITIVE LOGITS
     proceeded
    1.10
     proceed
    1.07
    proceed
    0.94
     proceeding
    0.91
     proceeds
    0.90
     onto
    0.86
     Proceed
    0.85
     PROCEED
    0.84
     procede
    0.80
    Proceed
    0.80
    Activations Density 0.730%

    No Known Activations