© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 41-GEMMASCOPE-RES-16K
    6. 7043
    Prev
    Next
    INDEX
    Explanations

    elements related to requests and inquiries in communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     me
    -0.90
    me
    -0.90
     comigo
    -0.83
     meiner
    -0.79
     мне
    -0.79
    Me
    -0.78
    você
    -0.77
     meinem
    -0.75
    Myself
    -0.75
    Você
    -0.74
    POSITIVE LOGITS
     us
    2.03
     нас
    0.63
     use
    0.56
     usan
    0.54
     uso
    0.47
    InputBorder
    0.44
    مان
    0.43
     ú
    0.42
     usare
    0.42
    balleur
    0.41
    Activations Density 0.178%

    No Known Activations