© 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. 21-GEMMASCOPE-RES-16K
    11. 5125
    Prev
    Next
    INDEX
    Explanations

    terms associated with legal and medical contexts, particularly regarding options, employment, and health services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IBOutlet
    -0.51
    才能
    -0.46
    toir
    -0.46
    erweise
    -0.44
    ずに
    -0.43
    locken
    -0.43
    Lähteet
    -0.43
    ethene
    -0.41
    才可以
    -0.41
    oster
    -0.40
    POSITIVE LOGITS
     any
    3.64
    Any
    3.07
    any
    3.03
     anything
    2.98
     Any
    2.94
     ANY
    2.89
     anyone
    2.86
     cualquier
    2.77
     qualquer
    2.76
     anybody
    2.74
    Activations Density 1.041%

    No Known Activations