© 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. 6-GEMMASCOPE-RES-16K
    6. 1236
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the concept of 'a' or 'an' followed by various descriptors or subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Portály
    -0.90
     Houſe
    -0.85
     indépendante
    -0.78
     Efq
    -0.73
     ſtate
    -0.73
     houſe
    -0.73
     indipendente
    -0.72
     myſelf
    -0.71
    antMatchers
    -0.71
     fince
    -0.71
    POSITIVE LOGITS
    ществует
    0.61
    hamel
    0.57
    kere
    0.57
    randall
    0.55
     exists
    0.55
    有一個
    0.55
     right
    0.55
    HtmlAttribute
    0.55
     special
    0.53
     very
    0.53
    Activations Density 0.145%

    No Known Activations