© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 1446
    Prev
    Next
    INDEX
    Explanations

    instances of the word "since" and its variations, indicating a focus on temporal relationships or causal events

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    Follows the word "since"

    np_acts-logits-general · gemini-2.0-flash

    since it

    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
    Negative Logits
    ]--;
    -0.67
     CanadaChoose
    -0.66
    canActivate
    -0.66
     Conseils
    -0.65
    expandindo
    -0.64
    oredCriteria
    -0.63
     Fails
    -0.62
    TagHelpers
    -0.62
     Waray
    -0.62
    RTEE
    -0.60
    POSITIVE LOGITS
     then
    0.74
    })`
    0.65
     forth
    0.65
     anteriore
    0.63
    awtextra
    0.63
     então
    0.62
    ithi
    0.60
     attendre
    0.59
     صوتيه
    0.59
     cedo
    0.58
    Activations Density 0.160%

    No Known Activations