© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 14369
    Prev
    Next
    INDEX
    Explanations

    mentions of people and their perspectives or actions in various contexts

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

    "Many [group of people]"

    np_acts-logits-general · gemini-2.0-flash

    many [group] [verb]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     anything
    -0.79
     anyone
    -0.73
    anyone
    -0.70
    Anything
    -0.70
     any
    -0.70
    anything
    -0.69
     Anything
    -0.68
     mostly
    -0.68
     Anyone
    -0.67
     Cualquier
    -0.67
    POSITIVE LOGITS
     including
    0.76
     either
    0.73
    including
    0.72
     Either
    0.70
    INCLUDING
    0.68
    either
    0.67
    Either
    0.64
     Including
    0.64
     choose
    0.63
    甚至是
    0.62
    Activations Density 0.344%

    No Known Activations