© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 11081
    Prev
    Next
    INDEX
    Explanations

    terms related to ratings, releases, and broadcast information for shows and episodes

    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
    rmtree
    -0.49
     
    -0.48
    Override
    -0.45
    した
    -0.45
    ,
    -0.44
    ontale
    -0.44
    stornos
    -0.43
     amare
    -0.43
     ronda
    -0.42
     reale
    -0.42
    POSITIVE LOGITS
     Мексичка
    0.93
    ]")]
    0.89
    ientôt
    0.82
     дописавши
    0.76
     Seeder
    0.75
    تقاوى
    0.74
    цездатний
    0.73
    úsqueda
    0.72
    scriptId
    0.71
     getF
    0.71
    Activations Density 0.072%

    No Known Activations