© 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. 0-GEMMASCOPE-RES-16K
    11. 2731
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate fulfillment or compliance with criteria or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     staden
    -0.54
     temporaire
    -0.51
     duquel
    -0.51
     vertrouwen
    -0.49
     zelve
    -0.48
     respectivement
    -0.47
     kracht
    -0.47
     vägen
    -0.46
     fréquent
    -0.46
     belangrij
    -0.45
    POSITIVE LOGITS
    TagMode
    0.78
    MLLoader
    0.68
    +#+
    0.63
    DataAnnotations
    0.61
    libft
    0.59
    stdc
    0.59
    EndTag
    0.59
    endcsname
    0.57
    LookAnd
    0.55
    InitStruct
    0.54
    Activations Density 0.233%

    No Known Activations