© 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. 6821
    Prev
    Next
    INDEX
    Explanations

    terms related to publication, authorship, and documentation

    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
    đe
    -0.49
     للاسماء
    -0.42
    oncesto
    -0.42
     związane
    -0.42
    barung
    -0.40
    ことができました
    -0.40
     يتيمه
    -0.40
    ことができます
    -0.39
     dotyczące
    -0.38
    ofing
    -0.38
    POSITIVE LOGITS
    ness
    0.93
     anteriormente
    0.73
     by
    0.68
     propOrder
    0.61
     вами
    0.60
     version
    0.57
    s
    0.56
     versions
    0.56
    NESS
    0.56
    ByUser
    0.56
    Activations Density 1.040%

    No Known Activations