© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 9786
    Prev
    Next
    INDEX
    Explanations

    negative phrases or concepts related to limitations and failure

    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
    ftagPool
    -0.70
    verifyException
    -0.68
    verwijspagina
    -0.67
    MLLoader
    -0.66
     كومونز
    -0.61
    oa̍t
    -0.61
    MigrationBuilder
    -0.61
     surla
    -0.60
     الرياضيه
    -0.59
     Photocase
    -0.58
    POSITIVE LOGITS
     فار
    0.35
     pierdas
    0.34
    owice
    0.32
     cesse
    0.32
    っぱ
    0.31
    hésite
    0.31
     ſtand
    0.31
    sleeping
    0.30
     paja
    0.30
     idle
    0.30
    Activations Density 0.287%

    No Known Activations