© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 12237
    Prev
    Next
    INDEX
    Explanations

    topics related to claims, applications, or requests within bureaucratic or regulatory contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    exitRule
    -0.53
    ::_('
    -0.49
    发表于
    -0.48
    PreExecute
    -0.48
     ContentValues
    -0.47
    atother
    -0.46
    gameserver
    -0.45
     propOrder
    -0.45
    CTYPE
    -0.45
     ISNI
    -0.44
    POSITIVE LOGITS
     reminis
    0.84
     nostalgic
    0.81
     nostalgia
    0.79
     remembering
    0.78
     former
    0.78
    Former
    0.74
     nostal
    0.72
     Former
    0.70
     memories
    0.69
     throwback
    0.68
    Activations Density 0.662%

    No Known Activations