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. 2055
    Prev
    Next
    INDEX
    Explanations

    descriptions related to performance and versatility of vehicles

    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
    Referanser
    -0.43
     Rodríguez
    -0.37
     Esposito
    -0.37
     implements
    -0.37
     menyem
    -0.36
     Rosenthal
    -0.36
     Goldstein
    -0.36
     Méndez
    -0.36
     palk
    -0.35
     Rodriguez
    -0.35
    POSITIVE LOGITS
     BoxFit
    0.65
    #+#
    0.60
    ftagPool
    0.57
     Chwiliwch
    0.57
    AddTagHelper
    0.56
     quarries
    0.56
    chyma
    0.56
     ModelExpression
    0.55
     queſta
    0.54
    TagMode
    0.53
    Activations Density 0.283%

    No Known Activations