© 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. 9-GEMMASCOPE-RES-16K
    6. 8353
    Prev
    Next
    INDEX
    Explanations

    terminology related to the production and processing of materials or results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     T
    -0.64
     a
    -0.63
     A
    -0.63
     
    -0.59
     (
    -0.58
     an
    -0.58
     The
    -0.56
    inquirer
    -0.56
     another
    -0.53
     the
    -0.52
    POSITIVE LOGITS
     myſelf
    1.37
     itſelf
    1.27
     Jefus
    1.24
     raiſ
    1.19
     poffible
    1.17
     uſed
    1.17
     Efq
    1.14
     ſeveral
    1.13
     ་་
    1.12
    ſelf
    1.11
    Activations Density 0.634%

    No Known Activations