© 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 EvalsExportsinterp-engineNEWAPI 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. 12404
    Prev
    Next
    INDEX
    Explanations

    predicates and conjugated verbs in various tenses

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

    French "je suis" (I am)

    np_acts-logits-general · gemini-2.0-flash

    je suis + état

    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
     disparu
    -0.65
     picioare
    -0.62
    AddTagHelper
    -0.61
    posedge
    -0.61
    Newest
    -0.59
    webElementXpaths
    -0.59
    Cyfarwyddwr
    -0.56
    ThroughAttribute
    -0.56
     nessuna
    -0.54
     chaleureux
    -0.54
    POSITIVE LOGITS
    GeneratedCode
    0.63
     uska
    0.56
     sinon
    0.55
     nakalista
    0.54
    ICIOS
    0.53
     moreover
    0.51
    ToBe
    0.51
     endforeach
    0.50
     Cymru
    0.50
     }}=\
    0.49
    Activations Density 0.080%

    No Known Activations