© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 15583
    Prev
    Next
    INDEX
    Explanations

    relationships involving cause and effect, particularly those associated with changes and their likely consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     незавершена
    -0.45
    ustainable
    -0.40
    Referanser
    -0.37
     conno
    -0.36
    pushFollow
    -0.35
     gogh
    -0.35
    ſtre
    -0.33
     interse
    -0.33
     walkthrough
    -0.32
    ondissement
    -0.32
    POSITIVE LOGITS
    sizeCache
    0.78
    ValueStyle
    0.71
     partly
    0.60
    +#+#
    0.57
    ArgsConstructor
    0.55
    partly
    0.54
    IsContent
    0.54
     largely
    0.54
     يتيمه
    0.54
    PyExc
    0.53
    Activations Density 0.383%

    No Known Activations