© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 9146
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "man" or "male presence" in the context of life and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    qJ
    -0.43
    :+:
    -0.43
     seed
    -0.41
    Décès
    -0.41
    EIF
    -0.40
    Filmografia
    -0.39
    SuspendLayout
    -0.38
    ByteBuf
    -0.37
    Clima
    -0.37
    IGENCE
    -0.37
    POSITIVE LOGITS
     man
    0.73
    Бахар
    0.63
     supports
    0.56
    achau
    0.51
    Referències
    0.49
    supports
    0.48
     adulthood
    0.45
    Datuak
    0.44
     greatness
    0.44
     asked
    0.43
    Activations Density 0.098%

    No Known Activations