© 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. 35-GEMMASCOPE-RES-16K
    6. 6476
    Prev
    Next
    INDEX
    Explanations

    phrases that refer to individuals or groups

    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
     which
    -0.72
     laquelle
    -0.50
    which
    -0.46
     WHICH
    -0.42
     mounting
    -0.38
    tu
    -0.38
    tổng
    -0.36
     IBOutlet
    -0.36
    Which
    -0.36
     للاسماء
    -0.36
    POSITIVE LOGITS
     who
    0.70
     którzy
    0.70
     whom
    0.64
     ktorí
    0.61
    FunctionFlags
    0.61
     quienes
    0.59
    whom
    0.59
     kteří
    0.59
    CloseOperation
    0.58
     queſta
    0.58
    Activations Density 0.180%

    No Known Activations