© 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. 10-GEMMASCOPE-RES-16K
    6. 1623
    Prev
    Next
    INDEX
    Explanations

    phrases indicating inconsistent or conflicting research results and findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Alphabet
    -0.52
     beet
    -0.48
    handelt
    -0.46
    تقاوى
    -0.45
    ücken
    -0.42
     kuns
    -0.42
    ⏜
    -0.41
    cuits
    -0.40
     Закон
    -0.40
    Title
    -0.40
    POSITIVE LOGITS
    InjectAttribute
    0.76
    mybatisplus
    0.71
    SharedDtor
    0.71
     autorytatywna
    0.68
    flashdata
    0.63
    évaluateur
    0.63
    WebControls
    0.62
     RemoteException
    0.61
    protoimpl
    0.58
     endforeach
    0.57
    Activations Density 0.745%

    No Known Activations