© 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. 7-GEMMASCOPE-RES-16K
    6. 12181
    Prev
    Next
    INDEX
    Explanations

    phrases related to statements and assertions made by individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tymologie
    -0.62
    urcht
    -0.60
     voulez
    -0.52
    ولات
    -0.51
     eficientes
    -0.50
     aient
    -0.49
    ".$_
    -0.48
    FIRST
    -0.47
    einem
    -0.45
    一场
    -0.45
    POSITIVE LOGITS
     added
    0.99
     ADDED
    0.89
     Added
    0.89
    وأضاف
    0.87
     añadió
    0.86
    MethodManager
    0.82
    Added
    0.82
     добавил
    0.80
     kaynağından
    0.77
     adds
    0.76
    Activations Density 0.068%

    No Known Activations