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. 117339
    Prev
    Next
    INDEX
    Explanations

    references to memory and data operations in technical contexts

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

    Technical terminology related to memory operations and computing parameters in structured documentation, often appearing in XML-like configuration code or technical writing about computational processes.

    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
    เอง
    -0.33
     heard
    -0.33
    เป
    -0.33
     honour
    -0.31
     met
    -0.31
     acep
    -0.30
    ◡
    -0.29
     hear
    -0.29
    met
    -0.28
     vid
    -0.28
    POSITIVE LOGITS
    OGND
    0.70
    exitRule
    0.63
    yntaxException
    0.62
    postIndex
    0.60
    contentLoaded
    0.60
     الرياضيه
    0.59
     Chwiliwch
    0.59
    AddTagHelper
    0.59
     Normdatei
    0.57
    styleType
    0.56
    Activations Density 0.267%

    No Known Activations