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-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 5811
    Prev
    Next
    INDEX
    Explanations

    phrases related to web references and citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ‘
    -0.52
     f
    -0.52
     I
    -0.52
     J
    -0.51
     W
    -0.51
     “
    -0.48
    ="../
    -0.47
     F
    -0.46
     no
    -0.46
    5
    -0.46
    POSITIVE LOGITS
    consulté
    2.40
     consultato
    2.12
     Процитовано
    1.74
     abgerufen
    1.73
     Consultado
    1.66
     оригіналу
    1.54
     Abgerufen
    1.43
    Hozzáférés
    1.42
     الاطلاع
    1.40
     Accesat
    1.38
    Activations Density 0.007%

    No Known Activations