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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 13458
    Prev
    Next
    INDEX
    Explanations

    keywords related to organizational structure and decision-making processes

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

    "...operations" or "...work"

    np_acts-logits-general · gemini-2.0-flash

    daily operations

    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
    •Steering experiments: Gemma 2-2B / 10-GEMMASCOPE-RES-16K

    No Comments

    Negative Logits
    rungsseite
    -0.66
     שוליים
    -0.61
     nakalista
    -0.58
    BASELINE
    -0.50
    tagHelperRunner
    -0.50
    tigte
    -0.48
     irony
    -0.47
    ellees
    -0.47
     unknownFields
    -0.46
    phoric
    -0.45
    POSITIVE LOGITS
     operations
    1.39
     activities
    1.35
    activities
    1.15
     functions
    1.13
    operations
    1.10
     activités
    1.08
     operation
    0.95
     programs
    0.93
     programmes
    0.92
     operational
    0.92
    Activations Density 0.289%

    No Known Activations