© 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-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 8792
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to natural qualities and phenomena

    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
     صوتيه
    -0.92
     chrétienne
    -0.86
    SBATCH
    -0.84
     ***!
    -0.84
     ويكيپيديا
    -0.84
     كومونز
    -0.83
    <caption>
    -0.83
     Shimano
    -0.82
    endpush
    -0.82
    ribune
    -0.81
    POSITIVE LOGITS
     natural
    1.32
     Natural
    1.22
    natural
    1.10
    NATURAL
    1.07
    Natural
    1.07
     NATURAL
    1.05
     Natur
    1.03
     natur
    0.99
     natu
    0.93
    Natur
    0.91
    Activations Density 0.069%

    No Known Activations