© 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. 5-GEMMASCOPE-RES-16K
    6. 12364
    Prev
    Next
    INDEX
    Explanations

    patterns related to medical or biological terms and their classifications

    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
    parsedMessage
    -0.85
    InputTagHelper
    -0.82
    EndInit
    -0.82
     autorytatywna
    -0.78
    Filmographie
    -0.73
    ])));
    -0.71
     ProtoMessage
    -0.71
    IsContent
    -0.70
     verwijzen
    -0.69
    ligators
    -0.68
    POSITIVE LOGITS
    +:+
    0.85
     AspNetCore
    0.63
     ögon
    0.61
    konos
    0.59
    спол
    0.58
     kone
    0.57
     Marlon
    0.56
     stesse
    0.56
    Độ
    0.55
    jenigen
    0.55
    Activations Density 0.196%

    No Known Activations