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 - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 6293
    Prev
    Next
    INDEX
    Explanations

    details about economic transactions and contracts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     offenbar
    -0.61
     särskilt
    -0.60
     variously
    -0.55
     freilich
    -0.53
     quoque
    -0.52
     similarly
    -0.51
     zunächst
    -0.50
     ostensibly
    -0.49
     conspicuously
    -0.49
     zwykle
    -0.49
    POSITIVE LOGITS
    慢慢的
    0.75
    非常的
    0.73
    +#+#
    0.68
    utilizzo
    0.64
    webElementXpaths
    0.61
     everytime
    0.61
    complexContent
    0.60
     alot
    0.60
    ########.
    0.60
    不断的
    0.59
    Activations Density 7.162%

    No Known Activations