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. 20-GEMMASCOPE-RES-16K
    6. 6340
    Prev
    Next
    INDEX
    Explanations

    instances of the letter 's' in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Theſe
    -0.68
    ه
    -0.67
    tling
    -0.65
    i
    -0.65
    y
    -0.64
    urally
    -0.63
    e
    -0.61
    arity
    -0.59
    ously
    -0.58
    ingly
    -0.58
    POSITIVE LOGITS
     nakalista
    1.07
    LookAnd
    1.00
    MigrationBuilder
    0.95
     للمعارف
    0.88
     متعلقه
    0.85
    GEBURTSDATUM
    0.84
    XmlAccessType
    0.84
    IUrlHelper
    0.84
    
    0.83
     AssemblyCulture
    0.83
    Activations Density 0.355%

    No Known Activations