© 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. 3701
    Prev
    Next
    INDEX
    Explanations

    references to specific locations, roles, or functions related to tasks and entities

    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
     myſelf
    -1.21
     itſelf
    -1.10
     $_"
    -1.09
     Theſe
    -1.06
     ſeveral
    -1.03
     poffible
    -0.99
     Monfieur
    -0.99
     whoſe
    -0.95
     Efq
    -0.94
     Reſ
    -0.93
    POSITIVE LOGITS
    <bos>
    0.58
    XtraEditors
    0.49
    '
    0.47
    ########.
    0.47
     cor
    0.46
     G
    0.46
     H
    0.45
    [
    0.45
     expédié
    0.44
     [
    0.43
    Activations Density 2.122%

    No Known Activations