© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 5-GEMMASCOPE-RES-16K
    11. 15210
    Prev
    Next
    INDEX
    Explanations

    phrases indicating ownership or belonging

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     purpoſe
    -0.85
     quæ
    -0.77
     ſtate
    -0.76
     houſe
    -0.71
     habet
    -0.71
     ſen
    -0.68
     tarko
    -0.65
    ſelf
    -0.63
     difp
    -0.62
     ſch
    -0.62
    POSITIVE LOGITS
    adpleegd
    0.82
    /#{
    0.75
     "..\..\
    0.74
    thâu
    0.74
    +#+
    0.74
    mphony
    0.73
    GOTREF
    0.71
     THAN
    0.70
    #+#
    0.69
    :+:
    0.66
    Activations Density 0.178%

    No Known Activations