© 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. 35-GEMMASCOPE-RES-16K
    11. 12633
    Prev
    Next
    INDEX
    Explanations

    references to players, particularly in the context of sports and healthcare

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fjspx
    -0.54
    WebServlet
    -0.48
     laço
    -0.41
     ře
    -0.38
    setLength
    -0.37
    adpleegd
    -0.37
     relógio
    -0.36
     neón
    -0.35
    vées
    -0.35
     детская
    -0.35
    POSITIVE LOGITS
     getPlayer
    0.67
    Athlete
    0.56
     Player
    0.56
     Athlete
    0.54
    balleur
    0.51
    IBarButtonItem
    0.50
    Doe
    0.50
    getPlayer
    0.50
    Soldier
    0.49
    versary
    0.48
    Activations Density 0.501%

    No Known Activations