© 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. 4129
    Prev
    Next
    INDEX
    Explanations

    references to offices or office-related settings

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

    Following the word "office"

    np_acts-logits-general · gemini-2.0-flash

    office and its common collocations

    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
     resourceCulture
    -0.83
    ness
    -0.61
     ContentValues
    -0.57
    OwnProperty
    -0.56
    bewerken
    -0.55
    ly
    -0.55
    ség
    -0.55
    nt
    -0.54
     ProtoMessage
    -0.54
    office
    -0.53
    POSITIVE LOGITS
    Demografía
    0.74
    holders
    0.74
    holder
    0.73
     bearers
    0.70
     hours
    0.67
    bearers
    0.65
     Hours
    0.65
    DotNetBar
    0.61
    hours
    0.60
     SEDS
    0.59
    Activations Density 0.094%

    No Known Activations