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. 17-GEMMASCOPE-RES-16K
    6. 5969
    Prev
    Next
    INDEX
    Explanations

    references to "man" in various contexts, often related to legal terms or names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CloseOperation
    -0.76
    lamabad
    -0.73
     оригіналу
    -0.69
    хьтан
    -0.67
     biber
    -0.64
    imageshack
    -0.63
     Ezek
    -0.63
    istoitu
    -0.62
    ContentAsync
    -0.60
    StoryboardSegue
    -0.60
    POSITIVE LOGITS
     Man
    0.93
    Man
    0.91
     MAN
    0.91
     man
    0.84
    man
    0.76
    MAN
    0.71
    Mano
    0.66
     mans
    0.65
     مان
    0.63
     Mann
    0.63
    Activations Density 0.211%

    No Known Activations