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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 481
    Prev
    Next
    INDEX
    Explanations

    elements related to witness statements and legal testimonies

    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
     CreateTagHelper
    -1.16
    ViewFeatures
    -0.87
    setVerticalGroup
    -0.86
    :✨
    -0.85
    AndEndTag
    -0.83
     Roskov
    -0.79
     '\\;'
    -0.79
    AnchorStyles
    -0.75
     виправивши
    -0.74
    EndInit
    -0.73
    POSITIVE LOGITS
    sic
    1.16
    中略
    1.16
     itſelf
    0.81
    ,]
    0.79
    inaudible
    0.78
     ...]
    0.73
     pleaſure
    0.73
    ..]
    0.71
     dumne
    0.68
    ...]
    0.68
    Activations Density 0.127%

    No Known Activations