Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 8306
    Prev
    Next
    INDEX
    Explanations

    references to the concept of resolution in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    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
    -0.74
     "..\..\
    -0.69
    QMetaType
    -0.65
     useAppContext
    -0.63
     Walkover
    -0.62
    DispatchToProps
    -0.62
    OGND
    -0.61
    Chham
    -0.60
    Identyfik
    -0.59
    abancı
    -0.59
    POSITIVE LOGITS
     bağlantılar
    0.77
    ful
    0.67
    fulness
    0.66
     šal
    0.58
    fully
    0.58
     SMD
    0.56
     للاسماء
    0.54
    ++++++++
    0.53
     humaines
    0.52
    esgue
    0.51
    Activations Density 0.181%

    No Known Activations