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-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 2854
    Prev
    Next
    INDEX
    Explanations

    the presence of certain French language words, particularly articles and pronouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    s
    -0.70
     Nie
    -0.67
     Nye
    -0.66
     "
    -0.65
    koda
    -0.63
    MigrationBuilder
    -0.63
    =>'
    -0.63
     merce
    -0.62
     “
    -0.61
     vore
    -0.61
    POSITIVE LOGITS
     nakalista
    1.01
    SequentialGroup
    0.92
    𝙫
    0.87
     المعيارى
    0.87
     متعلقه
    0.87
     مشين
    0.85
    первых
    0.85
    jusqu
    0.84
    NewGuid
    0.83
    nvarchar
    0.82
    Activations Density 0.085%

    No Known Activations