© 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. 38-GEMMASCOPE-RES-16K
    6. 9770
    Prev
    Next
    INDEX
    Explanations

    phrases questioning the extent or degree of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſche
    -0.47
    DIPSETTING
    -0.43
     cession
    -0.43
     purpoſe
    -0.42
     useAppContext
    -0.42
     molt
    -0.42
     ſte
    -0.42
     PhpStorm
    -0.41
     houſe
    -0.40
     cauſe
    -0.39
    POSITIVE LOGITS
     annoying
    0.68
     scary
    0.68
     embarrassing
    0.66
     hilarious
    0.66
     thrilled
    0.65
     terrified
    0.65
     disgusted
    0.64
     nødven
    0.63
     frustrating
    0.63
     excited
    0.63
    Activations Density 0.677%

    No Known Activations