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-2-2B
    4. Residual Stream - 16k
    5. 6-GEMMASCOPE-RES-16K
    6. 2564
    Prev
    Next
    INDEX
    Explanations

    HTML line break tags

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    {(-
    -0.73
    icylic
    -0.61
    ={`
    -0.60
     заве
    -0.58
     {(
    -0.58
     bit
    -0.58
    ailleurs
    -0.58
    deed
    -0.58
    hit
    -0.58
    episode
    -0.57
    POSITIVE LOGITS
    br
    1.92
     br
    1.40
    Br
    1.40
     Br
    1.33
    BR
    1.10
     BR
    1.04
     Brind
    0.98
     brz
    0.89
     Brü
    0.88
     Brink
    0.85
    Activations Density 0.025%

    No Known Activations