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
    4. Residual Stream - 131k
    5. 24-GEMMASCOPE-RES-131K
    6. 986
    Prev
    Next
    INDEX
    Explanations

    parts of mathematical and programming syntax

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

    mathematical and statistical parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.60
    AsUp
    -0.57
     tartalomajánló
    -0.53
     chi̍t
    -0.52
    UnusedPrivate
    -0.50
    Autoritní
    -0.49
    κης
    -0.49
    astéroïdes
    -0.48
    tanleria
    -0.48
    testens
    -0.47
    POSITIVE LOGITS
     שוליים
    0.44
     kaarangay
    0.40
    性和
    0.39
    さと
    0.39
    Lähteet
    0.38
    verwijspagina
    0.37
     its
    0.36
    IonicModule
    0.36
     يتيمه
    0.35
    routeProvider
    0.35
    Activations Density 0.053%

    No Known Activations