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. 14973
    Prev
    Next
    INDEX
    Explanations

    URLs or references that denote digital links

    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
    MessageTagHelper
    -1.03
     CanadaChoose
    -1.02
     OFDb
    -1.01
    Rohy
    -0.88
    ArrowToggle
    -0.87
    principalTable
    -0.84
    Vidite
    -0.83
     BorderRadius
    -0.83
     Italijani
    -0.82
    webElement
    -0.82
    POSITIVE LOGITS
    \\[
    0.72
    u
    0.69
    CJK
    0.66
     \\[
    0.62
     محفوظة
    0.60
     Geschä
    0.59
    keits
    0.59
    amarin
    0.54
    anthin
    0.54
    <0xD4>
    0.52
    Activations Density 0.037%

    No Known Activations