© 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. 41-GEMMASCOPE-RES-16K
    11. 7615
    Prev
    Next
    INDEX
    Explanations

    concepts related to choices and their impacts on life scenarios

    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
    They
    -0.71
    He
    -0.68
    She
    -0.60
    You
    -0.58
     THEM
    -0.57
     surla
    -0.55
    Mereka
    -0.54
    them
    -0.53
    AndEndTag
    -0.51
     "..\..\..\
    -0.50
    POSITIVE LOGITS
     we
    3.55
     мы
    1.37
    我們
    1.23
    我们
    1.19
    เรา
    1.11
    We
    1.01
    私たちは
    0.97
     हम
    0.96
     chúng
    0.96
     abbiamo
    0.93
    Activations Density 1.516%

    No Known Activations