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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 3-GEMMASCOPE-RES-16K
    6. 12826
    Prev
    Next
    INDEX
    Explanations

    programming structures related to functional programming, particularly higher-order functions and their applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     دیکھیے
    -0.80
    featureID
    -0.71
    WebControls
    -0.56
    الدراسه
    -0.56
    AccessorTable
    -0.54
    aarrggbb
    -0.54
    __":
    
    -0.52
     Shirley
    -0.52
     للاسماء
    -0.51
    hbase
    -0.50
    POSITIVE LOGITS
    AxisAlignment
    0.76
     wireType
    0.69
     BoxFit
    0.65
     TextInputType
    0.61
     IndexPath
    0.57
    CheckedChanged
    0.56
     BoxDecoration
    0.54
    󠁧
    0.53
    InputBorder
    0.53
     générations
    0.53
    Activations Density 0.091%

    No Known Activations