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. 12427
    Prev
    Next
    INDEX
    Explanations

    concepts related to system performance and interactions

    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
     disambiguazione
    -0.97
     utafitiHapana
    -0.66
     kasarigan
    -0.63
    homonymie
    -0.63
    IBOutlet
    -0.62
    ReusableCell
    -0.61
    ьаж
    -0.58
    bewerken
    -0.57
     estekak
    -0.56
    WriteBarrier
    -0.53
    POSITIVE LOGITS
     détect
    0.36
     flows
    0.36
     frío
    0.33
     semejante
    0.33
     spotted
    0.32
     fine
    0.32
    脉
    0.32
     succès
    0.31
     obligado
    0.31
     Yet
    0.31
    Activations Density 1.181%

    No Known Activations