© 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. 15700
    Prev
    Next
    INDEX
    Explanations

    words related to concepts of "propensity" and "propulsion."

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

    Following "Prop" or "prop" (case-insensitive)

    np_acts-logits-general · gemini-2.0-flash

    words beginning with the prop prefix

    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
     <=",
    -0.71
     proposto
    -0.71
     propuesta
    -0.70
     ProtoMessage
    -0.70
     propuestas
    -0.69
    Practical
    -0.67
     proposta
    -0.66
     proposal
    -0.65
    .*")]
    -0.65
     NSCoder
    -0.64
    POSITIVE LOGITS
     nouns
    0.55
    ensity
    0.51
     intellectuelle
    0.49
     Weit
    0.49
    bably
    0.48
     noun
    0.48
     Casualty
    0.48
    iedad
    0.47
     Gelder
    0.46
     Pik
    0.46
    Activations Density 0.291%

    No Known Activations