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. 10-GEMMASCOPE-RES-16K
    6. 4453
    Prev
    Next
    INDEX
    Explanations

    technical terms related to coding and programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HasForeignKey
    -0.68
     '{@
    -0.59
    այ
    -0.57
     welcome
    -0.56
    ắt
    -0.55
    leih
    -0.54
    ,"%
    -0.53
     dek
    -0.53
     SearchView
    -0.52
     thereafter
    -0.52
    POSITIVE LOGITS
    unfinished
    3.91
     unfinished
    2.15
    Unfinished
    1.73
    未完
    0.99
     incomplete
    0.90
    incomplete
    0.84
    FINISHED
    0.84
    finished
    0.83
     Incomplete
    0.83
    发表于
    0.80
    Activations Density 0.016%

    No Known Activations