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. 16-GEMMASCOPE-RES-16K
    6. 1840
    Prev
    Next
    INDEX
    Explanations

    instances of the word "someone" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Sentences starting with "Someone," "Anyone," or "No one."

    np_acts-logits-general · gemini-2.0-flash

    Someone/Anyone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Datuak
    -0.60
     Zah
    -0.58
    itres
    -0.56
     Bergh
    -0.54
     matter
    -0.53
    mts
    -0.53
    TagHelpers
    -0.52
     Spire
    -0.52
    UVWXYZ
    -0.51
    )_{
    -0.51
    POSITIVE LOGITS
     else
    1.46
    Else
    1.00
     who
    0.96
     ELSE
    0.93
     Else
    0.92
    Somebody
    0.92
     Nadie
    0.91
    Nobody
    0.90
    Anybody
    0.89
     Somebody
    0.89
    Activations Density 0.051%

    No Known Activations