© 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. 3-GEMMASCOPE-RES-16K
    11. 9708
    Prev
    Next
    INDEX
    Explanations

    chemical components related to specific reagents and their functions in biological experiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]}"
    -0.73
    }))
    -0.71
    Personensuche
    -0.66
    Theo
    -0.66
     CanadaChoose
    -0.65
    parsedMessage
    -0.63
     doInBackground
    -0.62
    }));
    -0.61
    undial
    -0.60
    abestanden
    -0.59
    POSITIVE LOGITS
    iz
    1.39
    IZ
    1.19
    Iz
    1.17
    uz
    1.17
     Iz
    1.16
    tz
    1.14
    lez
    1.07
    waz
    1.06
     Tiz
    1.04
    UZ
    1.04
    Activations Density 0.272%

    No Known Activations