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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 12860
    Prev
    Next
    INDEX
    Explanations

    terms related to medical and physiological conditions, particularly those involving surgery and anatomical structures

    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
     Simmons
    -0.70
    @@@@@@@@
    -0.70
    <blockquote>
    -0.69
    iiiiiiii
    -0.66
    laag
    -0.66
     dép
    -0.65
    ď
    -0.65
    Cordialement
    -0.64
    zoek
    -0.64
    tramp
    -0.64
    POSITIVE LOGITS
     bezeichneter
    1.01
    Datuak
    0.98
     Idio
    0.90
     ModelRenderer
    0.90
     acorn
    0.89
     Prato
    0.88
     оригіналу
    0.88
     majeur
    0.87
    nament
    0.86
     Bronson
    0.85
    Activations Density 11.468%

    No Known Activations