© 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. 22-GEMMASCOPE-RES-16K
    11. 1812
    Prev
    Next
    INDEX
    Explanations

    questions regarding the necessity and feasibility of actions or decisions

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

    "Is it" precedes an adjective

    np_acts-logits-general · gemini-2.0-flash

    is it possible/necessary/practical

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    almost
    -0.84
    Almost
    -0.75
     Sehr
    -0.73
     almost
    -0.71
     quase
    -0.69
     Almost
    -0.68
    very
    -0.68
     excellently
    -0.66
    meist
    -0.65
    Very
    -0.64
    POSITIVE LOGITS
     ever
    1.14
     really
    1.08
     any
    1.08
     jemals
    1.08
     überhaupt
    1.03
     Really
    1.00
     truly
    0.99
     indeed
    0.98
     denn
    0.96
     acaso
    0.95
    Activations Density 0.394%

    No Known Activations