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. 5714
    Prev
    Next
    INDEX
    Explanations

    computer programming code syntax and structures

    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
    addPreferredGap
    -0.50
     conditions
    -0.49
    ضي
    -0.48
     cog
    -0.46
     مشين
    -0.45
    存于互联网档案馆
    -0.45
     distance
    -0.45
    AfterEach
    -0.44
     condition
    -0.42
    ofluor
    -0.41
    POSITIVE LOGITS
    rungsseite
    0.89
    Personensuche
    0.77
     Normdatei
    0.67
    URLException
    0.61
     muualla
    0.59
     ddelweddau
    0.59
     héri
    0.58
     المعيارى
    0.57
     chrétiens
    0.57
     numéros
    0.57
    Activations Density 0.544%

    No Known Activations