© 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. 0-GEMMASCOPE-RES-16K
    11. 8742
    Prev
    Next
    INDEX
    Explanations

    references to global entities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jsPsych
    -0.49
     resort
    -0.45
     Person
    -0.44
    PerformLayout
    -0.43
     MV
    -0.43
     sb
    -0.42
     rated
    -0.41
    ="";
    -0.41
     rating
    -0.41
     POS
    -0.41
    POSITIVE LOGITS
    Globe
    0.80
     dinámico
    0.79
    Global
    0.78
     globales
    0.77
     globe
    0.73
    ⓧ
    0.72
     globes
    0.70
     inalámbrica
    0.70
     Globe
    0.69
    GLOBAL
    0.69
    Activations Density 0.239%

    No Known Activations