© 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. 1351
    Prev
    Next
    INDEX
    Explanations

    instances of the term "la" and variations of it, particularly in relation to titles or names

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

    "La" followed by other tokens

    np_acts-logits-general · gemini-2.0-flash

    words starting with "la" or "La"

    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
    findpost
    -0.99
    참고
    -0.91
    Datuak
    -0.89
    OGND
    -0.85
    KommentareTeilen
    -0.84
    initComponents
    -0.81
     resourceCulture
    -0.79
    ISupport
    -0.78
    Portale
    -0.78
     propOrder
    -0.77
    POSITIVE LOGITS
    la
    0.62
     la
    0.59
    La
    0.59
     Laf
    0.58
     LA
    0.57
    Laf
    0.57
     La
    0.55
    LA
    0.53
     LAP
    0.51
     ла
    0.50
    Activations Density 0.269%

    No Known Activations