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

    Neuronpedia

    Jacobian LensNEW
    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. 6726
    Prev
    Next
    INDEX
    Explanations

    key terms and phrases related to societal structures and dynamics, particularly concerning human relationships and experiences

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

    discussions about societal structures and individual experiences in relation to various systems

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

    Alternatives or replacements using "instead" or "rather"

    np_acts-logits-general · gemini-2.0-flash

    rather than instead

    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
    enderror
    -0.63
     nakalista
    -0.62
    InSection
    -0.55
     crossorigin
    -0.54
    mtable
    -0.52
    |}\
    -0.51
    人都
    -0.50
     Públicas
    -0.50
     Infórmanos
    -0.50
    ++
    -0.50
    POSITIVE LOGITS
     rather
    3.88
    rather
    3.42
     instead
    3.24
     Rather
    3.06
    Rather
    3.04
    instead
    2.96
     plutôt
    2.91
     anstatt
    2.62
    而不是
    2.55
    Instead
    2.52
    Activations Density 1.098%

    No Known Activations