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. 8-GEMMASCOPE-RES-16K
    6. 4788
    Prev
    Next
    INDEX
    Explanations

    assembly language instructions and related operational codes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ագրություններ
    -0.74
    脚注の使い方
    -0.57
    ichtet
    -0.55
     risco
    -0.55
    AccessorTable
    -0.54
    存于互联网档案馆
    -0.52
    Viitteet
    -0.51
    azgo
    -0.51
    près
    -0.50
     Nation
    -0.50
    POSITIVE LOGITS
    stdc
    0.65
    endphp
    0.64
    modelBuilder
    0.61
     :=
    0.58
     onBind
    0.56
     ControllerBase
    0.55
     kiệm
    0.53
    matchCondition
    0.53
    олові
    0.52
     intptr
    0.52
    Activations Density 0.473%

    No Known Activations