© 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-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 2157
    Prev
    Next
    INDEX
    Explanations

    words related to substitutions and replacements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     стаття
    -0.61
    TintMode
    -0.60
    клопе
    -0.59
    djangoproject
    -0.58
     calendriers
    -0.58
    SizeF
    -0.57
    olerance
    -0.57
    estimm
    -0.56
    TypedDataSet
    -0.56
     Numerology
    -0.55
    POSITIVE LOGITS
    EDEFAULT
    0.55
     oublier
    0.55
     missing
    0.53
     craindre
    0.53
     absent
    0.52
     equivalent
    0.47
    相当于
    0.46
     lazy
    0.45
    かね
    0.45
     substitute
    0.44
    Activations Density 0.635%

    No Known Activations