© 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-2-2B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 10193
    Prev
    Next
    INDEX
    Explanations

    phrases expressing a willingness to provide assistance or further details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     juges
    -0.42
    utnik
    -0.40
    zzar
    -0.40
     armées
    -0.40
     knap
    -0.40
    пен
    -0.40
     Menge
    -0.38
    ME
    -0.38
    loyment
    -0.37
    yorsunuz
    -0.37
    POSITIVE LOGITS
     whatever
    0.81
     gerne
    0.81
    =$?
    0.76
    whatever
    0.76
     gärna
    0.76
     Willing
    0.75
     whichever
    0.73
     willing
    0.72
     ويكيميديا
    0.72
    anything
    0.71
    Activations Density 0.222%

    No Known Activations