© 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. 18-GEMMASCOPE-RES-16K
    11. 9012
    Prev
    Next
    INDEX
    Explanations

    words related to decision-making and its consequences

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

    before "made" or "decisions"

    np_acts-logits-general · gemini-2.0-flash

    made decisions and mistakes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CodeAttribute
    -0.70
    醐
    -0.62
    complexContent
    -0.56
    *}$
    -0.54
     comigo
    -0.51
    @[+][
    -0.51
    jsxFileName
    -0.51
    ContentAsync
    -0.50
    dena
    -0.49
    abestanden
    -0.49
    POSITIVE LOGITS
     made
    1.35
    made
    1.18
     Made
    1.11
    Made
    1.08
     MADE
    1.07
    MADE
    0.97
    making
    0.84
    makers
    0.83
     сделан
    0.82
     makers
    0.81
    Activations Density 0.474%

    No Known Activations