Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3864
    Prev
    Next
    INDEX
    Explanations

    phrases and words expressing assurance or commitment

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

    assurances or warranties

    np_acts-logits-general · gemini-2.0-flash

    guarantee

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sendRedirect
    -0.44
    useNewUrlParser
    -0.41
     Demokratie
    -0.41
    rededor
    -0.40
    řeba
    -0.39
     trámites
    -0.39
     Erde
    -0.39
    ETHING
    -0.39
     Croce
    -0.38
     Económica
    -0.38
    POSITIVE LOGITS
     guarantee
    2.00
     Guarantee
    1.91
     guaranteed
    1.90
    Guarantee
    1.82
    guarantee
    1.80
     guaranteeing
    1.75
    Guaranteed
    1.75
     guarantees
    1.75
     Guaranteed
    1.73
     Guarante
    1.67
    Activations Density 0.234%

    No Known Activations