Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 6005
    Prev
    Next
    INDEX
    Explanations

    terms related to resistance and susceptibility in various contexts

    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
     felizes
    -0.67
    lück
    -0.67
     ویکی‌پدیای
    -0.62
    oubliez
    -0.61
     Dooley
    -0.60
     Toc
    -0.59
    JMenu
    -0.58
     McNally
    -0.57
    føl
    -0.57
     Fever
    -0.56
    POSITIVE LOGITS
     resistance
    3.39
     Resistance
    3.16
    Resistance
    3.00
    resistance
    2.97
     resist
    2.90
     RESISTANCE
    2.82
     resistances
    2.71
     resistant
    2.64
     Resist
    2.64
     RESIST
    2.63
    Activations Density 0.108%

    No Known Activations