© 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. 30-GEMMASCOPE-RES-16K
    11. 11359
    Prev
    Next
    INDEX
    Explanations

    references to older software or technologies, particularly focusing on their legacy status

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

    Referring to something outdated

    np_acts-logits-general · gemini-2.0-flash

    old, outdated, obsolete

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/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.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -0.52
    extAlignment
    -0.46
    yarnpkg
    -0.45
    isContained
    -0.45
    wargs
    -0.44
     Réponses
    -0.43
    exels
    -0.43
     MediatR
    -0.42
    SBATCH
    -0.42
    tagHelper
    -0.42
    POSITIVE LOGITS
     old
    2.38
     outdated
    2.27
     antiquated
    2.03
     older
    1.93
     obsolete
    1.91
    old
    1.86
     vecchi
    1.85
     OLD
    1.80
    古い
    1.80
     viejos
    1.79
    Activations Density 0.772%

    No Known Activations