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

    Neuronpedia

    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. 28-GEMMASCOPE-RES-16K
    11. 7224
    Prev
    Next
    INDEX
    Explanations

    modals and ability-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows "could" or "not"

    np_acts-logits-general · gemini-2.0-flash

    ability or inability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Paglinawan
    -0.57
    出版年
    -0.54
     snippetHide
    -0.52
    
    -0.52
    ngrx
    -0.50
    Autoritní
    -0.46
     utafitiHapana
    -0.45
     bParam
    -0.45
     HasFactory
    -0.44
     typelib
    -0.43
    POSITIVE LOGITS
     afford
    0.65
    afford
    0.53
     sustain
    0.50
    AutoresizingMask
    0.47
     tolerate
    0.46
     access
    0.44
     visualize
    0.42
     affording
    0.41
     physically
    0.41
     foresee
    0.40
    Activations Density 0.293%

    No Known Activations