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 - 131k
    5. 33-GEMMASCOPE-RES-131K
    6. 65796
    Prev
    Next
    INDEX
    Explanations

    references to accreditation and regulatory bodies related to specific academic programs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_131k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Referències
    -0.43
     Gaspar
    -0.40
    lawesi
    -0.40
    lesias
    -0.40
    Trama
    -0.39
    Gas
    -0.38
     faites
    -0.37
     Gas
    -0.36
    gas
    -0.36
     Loren
    -0.36
    POSITIVE LOGITS
     LEED
    0.65
     estekak
    0.59
     propOrder
    0.55
    fromnode
    0.52
     green
    0.52
    GEBURTSDATUM
    0.51
     certification
    0.50
     Green
    0.50
    AnchorTagHelper
    0.50
    绿
    0.49
    Activations Density 0.003%

    No Known Activations