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. 16256
    Prev
    Next
    INDEX
    Explanations

    phrases indicating control or dominance over something

    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
     дописавши
    -0.80
    HasAnnotation
    -0.68
    données
    -0.65
     nakalista
    -0.64
    цездатний
    -0.64
    Tikang
    -0.63
    InputTagHelper
    -0.62
    zeciw
    -0.61
    enderror
    -0.58
    tagHelperRunner
    -0.58
    POSITIVE LOGITS
     takeover
    1.47
     invaded
    1.10
     invade
    1.01
     domination
    0.90
     invasion
    0.89
     übernimmt
    0.87
     übernahm
    0.86
     invading
    0.86
     übernehmen
    0.85
     overtake
    0.80
    Activations Density 0.253%

    No Known Activations