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. 1-GEMMASCOPE-RES-16K
    6. 4609
    Prev
    Next
    INDEX
    Explanations

    Java programming structure and elements, particularly the main method and its components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gagné
    -0.53
    hassee
    -0.49
    タジー
    -0.48
    çük
    -0.46
     väg
    -0.45
    neous
    -0.44
    jména
    -0.43
     něj
    -0.43
    gese
    -0.43
     religieux
    -0.43
    POSITIVE LOGITS
    BeginContext
    1.55
    ⓧ
    1.51
    ContentAsync
    1.47
    AccessorTable
    1.31
     defaultstate
    1.27
    
    1.27
     propOrder
    1.24
    matchCondition
    1.23
    SourceChecksum
    1.22
    ScopeManager
    1.21
    Activations Density 0.210%

    No Known Activations