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 Post
    5. 12-GEMMASCOPE-RES-1M
    6. 508
    Prev
    Next
    INDEX
    Explanations

    opening and usage of code blocks or curly braces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_1m/average_l0_107
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    1,048,576
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -1.06
    Personendaten
    -0.91
    complexContent
    -0.84
     CreateTagHelper
    -0.81
    +#+#
    -0.81
     cherchés
    -0.81
    Autoritní
    -0.74
    GEBURTSDATUM
    -0.72
     AssemblyCulture
    -0.72
     ModelExpression
    -0.71
    POSITIVE LOGITS
     by
    0.56
    pmc
    0.48
     with
    0.46
     Fou
    0.46
     Baum
    0.45
    ťaž
    0.42
    Fou
    0.42
    tamina
    0.42
     fan
    0.41
    NotBe
    0.41
    Activations Density 0.002%

    No Known Activations