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. 25-GEMMASCOPE-RES-16K
    6. 10306
    Prev
    Next
    INDEX
    Explanations

    phrases related to branding and marketing services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Exacts
    -0.53
     Viator
    -0.51
    kespeare
    -0.49
     Hedges
    -0.49
    GetLength
    -0.48
    etCode
    -0.48
    parsedMessage
    -0.47
    pperware
    -0.47
    autos
    -0.46
    testcase
    -0.45
    POSITIVE LOGITS
     logo
    1.17
     graphic
    1.15
     typography
    1.14
     design
    1.12
     designers
    1.09
     logos
    1.08
     Illustrator
    1.07
     Graphic
    1.07
     Logo
    1.05
     Typography
    1.02
    Activations Density 0.265%

    No Known Activations