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. 12599
    Prev
    Next
    INDEX
    Explanations

    phrases referring to accountability and legal 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
    EndInit
    -0.85
    MessageTagHelper
    -0.84
    Personendaten
    -0.84
     pleaſure
    -0.82
    Diweddarwch
    -0.81
     houſe
    -0.77
     ſta
    -0.76
    principalTable
    -0.75
    最快更新
    -0.74
    ViewFeatures
    -0.74
    POSITIVE LOGITS
    AddHtmlAttribute
    0.50
     notamment
    0.49
     than
    0.45
     שוליים
    0.45
    着一
    0.44
     of
    0.43
     estekak
    0.42
     primarily
    0.40
    łę
    0.36
     oma
    0.36
    Activations Density 0.613%

    No Known Activations