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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 9568
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal rights and responsibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hentet
    -0.74
     NUKAT
    -0.69
    ValueStyle
    -0.61
     дописавши
    -0.61
     gynhyrchwyd
    -0.59
     poveznice
    -0.58
     picada
    -0.57
    InjectAttribute
    -0.57
     Chwiliwch
    -0.55
    DockStyle
    -0.52
    POSITIVE LOGITS
     abandoning
    1.74
     abandon
    1.64
     ditch
    1.53
    abandon
    1.47
     aband
    1.44
     abandoned
    1.44
     Abandon
    1.43
     abandonment
    1.40
     esche
    1.33
     Ditch
    1.32
    Activations Density 0.742%

    No Known Activations