© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 14837
    Prev
    Next
    INDEX
    Explanations

    references to social and political issues, particularly concerning voter sentiments and demographic concerns

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

    preceding verbs of obligation/intention

    np_acts-logits-general · gemini-2.0-flash

    groups flocking or gravitating

    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
     podjela
    -0.55
    Portale
    -0.54
    Erreferentziak
    -0.52
    Collegamenti
    -0.52
    AccessorTable
    -0.49
    httphttps
    -0.49
    ntos
    -0.46
    Географиясе
    -0.46
     Guin
    -0.45
     gynnwys
    -0.44
    POSITIVE LOGITS
     flock
    1.03
     flocked
    0.99
     clamor
    0.85
     overwhelmingly
    0.83
    flock
    0.81
     demanding
    0.74
     gravit
    0.73
    autique
    0.73
     Flock
    0.72
     flocks
    0.72
    Activations Density 0.367%

    No Known Activations