© 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. 7015
    Prev
    Next
    INDEX
    Explanations

    references to impact and consequences in various contexts

    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
    ThroughAttribute
    -0.49
    invokeLater
    -0.46
     חיצוניים
    -0.46
    どうやら
    -0.44
    艋
    -0.43
     ***!
    -0.42
    ună
    -0.41
     هستیم
    -0.41
     >=",
    -0.40
    #+#
    -0.40
    POSITIVE LOGITS
     would
    3.63
    would
    2.81
    Would
    2.61
     Would
    2.59
     WOULD
    2.33
     wouldn
    2.09
     würde
    1.99
     wäre
    1.91
     serait
    1.89
     sería
    1.88
    Activations Density 2.059%

    No Known Activations