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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 51922
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals with the title "Ms." followed by a name

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     Tartar
    -0.46
    Coordinate
    -0.44
    you
    -0.43
     rive
    -0.43
    Contain
    -0.42
     built
    -0.42
    define
    -0.41
    imbangan
    -0.40
     Tivoli
    -0.40
     Reinhardt
    -0.40
    POSITIVE LOGITS
     Ms
    0.98
     Mr
    0.81
    Ms
    0.80
     Mrs
    0.71
    Mr
    0.68
     Messrs
    0.65
     ms
    0.64
     Mme
    0.64
     ErrIntOverflow
    0.63
    SharedDtor
    0.63
    Activations Density 0.004%

    No Known Activations