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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 122668
    Prev
    Next
    INDEX
    Explanations

    concepts related to financial regulations and economic stability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text fragments that represent technical terms, system components, or parameters that serve important functional roles within their context, often appearing in specialized or technical documents.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCompany
    -0.65
    RenderAtEndOf
    -0.62
     كومونز
    -0.60
     OFDb
    -0.55
    AddTagHelper
    -0.52
    styleType
    -0.52
    uxxxx
    -0.52
    aarrggbb
    -0.51
    EndContext
    -0.51
    脚注の使い方
    -0.51
    POSITIVE LOGITS
    +#+#
    0.53
     pulses
    0.47
     pulse
    0.44
     препратки
    0.41
    pulse
    0.41
    RTGC
    0.40
    till
    0.39
     Pulse
    0.38
    webElementXpaths
    0.38
     splash
    0.38
    Activations Density 0.407%

    No Known Activations