Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 19-GEMMASCOPE-RES-16K
    6. 15904
    Prev
    Next
    INDEX
    Explanations

    references to papers and submissions in an academic context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fromnode
    -0.80
     devriez
    -0.60
    Hozzáférés
    -0.60
    BufferException
    -0.59
    IonicModule
    -0.57
     populaires
    -0.56
    ="#"><
    -0.56
     capables
    -0.54
     geldt
    -0.51
     JpaRepository
    -0.51
    POSITIVE LOGITS
    ografija
    0.61
    脚注の使い方
    0.60
     figures
    0.59
     draft
    0.59
     typos
    0.59
    riae
    0.57
     accepted
    0.57
     ACCEPT
    0.57
     Latex
    0.55
     corrected
    0.54
    Activations Density 0.119%

    No Known Activations