© 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. 16011
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions related to convergence rates in a function

    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
    BeginContext
    -0.50
     pilotes
    -0.50
     Grat
    -0.49
    UnknownFieldSet
    -0.45
    ordat
    -0.45
     Surya
    -0.44
     cortinas
    -0.43
    Grat
    -0.43
    Scri
    -0.42
     Gob
    -0.42
    POSITIVE LOGITS
     censiti
    0.74
     norms
    0.73
     norm
    0.67
    twimg
    0.64
    norms
    0.64
    XMLSchema
    0.64
     NORM
    0.62
     norme
    0.62
    клопе
    0.62
     norma
    0.61
    Activations Density 0.901%

    No Known Activations