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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 2353
    Prev
    Next
    INDEX
    Explanations

    instances of the verb 'speak' and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.87
     Jefus
    -0.85
    [--
    -0.83
     ſche
    -0.82
    waltung
    -0.76
     Etapa
    -0.75
     verily
    -0.73
     Noruega
    -0.73
     Maze
    -0.72
     dommage
    -0.72
    POSITIVE LOGITS
     speak
    2.29
     Speak
    2.13
     speaking
    2.13
     speaks
    2.05
     spoke
    2.02
    Speak
    1.96
     spoken
    1.81
    speak
    1.76
    speaking
    1.73
     Speaking
    1.72
    Activations Density 0.037%

    No Known Activations