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. 6307
    Prev
    Next
    INDEX
    Explanations

    programming constructs and definitions, particularly related to functions and variables

    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
     digital
    -0.47
     Digital
    -0.45
    ftn
    -0.42
    rop
    -0.40
    ढ़
    -0.39
     Ko
    -0.39
    mack
    -0.38
    Geplaatst
    -0.38
    妳
    -0.38
    rolled
    -0.38
    POSITIVE LOGITS
    __':
    0.85
    ScopeManager
    0.84
    تقاوى
    0.84
    uxxxx
    0.81
     onCreateView
    0.81
    ViewFeatures
    0.79
    Personendaten
    0.77
     يتيمه
    0.77
     مشين
    0.74
    fony
    0.74
    Activations Density 0.156%

    No Known Activations