© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 5001
    Prev
    Next
    INDEX
    Explanations

    whitespace or indentation characters in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VersionUID
    -0.80
    
    -0.80
    MessageTagHelper
    -0.79
     ब्रेकडाउन
    -0.79
     resourceCulture
    -0.79
    :"-"`
    -0.78
    <unused19>
    -0.77
    
    -0.77
    <unused73>
    -0.77
    <unused1>
    -0.77
    POSITIVE LOGITS
     selaku
    0.28
     „
    0.27
     prochaines
    0.26
     např
    0.25
    gebracht
    0.25
     verwacht
    0.24
     pungkas
    0.23
     nonché
    0.22
    StringTo
    0.21
     næste
    0.21
    Activations Density 0.510%

    No Known Activations