© 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. 4-GEMMASCOPE-RES-16K
    11. 3920
    Prev
    Next
    INDEX
    Explanations

    terms related to biological or medical contexts, particularly highlighting distinctions between different types of entities or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ppia
    -0.59
    ConstraintMaker
    -0.57
     sièges
    -0.49
    hoku
    -0.47
    stdafx
    -0.47
    applications
    -0.47
    Swal
    -0.47
     linearly
    -0.46
     iscri
    -0.46
    mpions
    -0.46
    POSITIVE LOGITS
     nonatomic
    0.78
     indirect
    0.74
    ########.
    0.72
    Indirect
    0.68
     Undeclared
    0.67
     unofficial
    0.65
     Indirect
    0.64
    rrggbb
    0.63
     nonverbal
    0.62
     indirec
    0.62
    Activations Density 1.498%

    No Known Activations