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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4653
    Prev
    Next
    INDEX
    Explanations

    terms related to framed artworks and their specifications

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

    near prepositions and conjunctions

    np_acts-logits-general · gemini-2.0-flash

    framed print or mount

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/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.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
    VersionUID
    -0.62
     /\.(
    -0.58
    脚注の使い方
    -0.56
    AddTagHelper
    -0.55
    OpenHelper
    -0.53
     Denied
    -0.53
     indisponible
    -0.53
    ValueStyle
    -0.52
    مصادر
    -0.50
    NewReader
    -0.49
    POSITIVE LOGITS
     hanging
    1.68
     hung
    1.61
     hangs
    1.58
     hang
    1.55
     wall
    1.51
     framed
    1.49
     Hanging
    1.49
     hanged
    1.40
    hanging
    1.40
    Hanging
    1.39
    Activations Density 0.134%

    No Known Activations