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. 11025
    Prev
    Next
    INDEX
    Explanations

    instances of the word "further" used in context, often indicating a continuation or expansion of a discussion

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

    Follows "further" or "Further"

    np_acts-logits-general · gemini-2.0-flash

    introducing further points

    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
     préfé
    -0.51
     ferdig
    -0.49
     ervoor
    -0.49
    ใหม่
    -0.47
    mainAxisSize
    -0.47
     passaram
    -0.47
     físicos
    -0.46
     thật
    -0.46
     setempat
    -0.46
     sehat
    -0.45
    POSITIVE LOGITS
     afield
    1.23
     ado
    0.83
    存于互联网档案馆
    0.80
    emore
    0.79
    TProtocol
    0.76
     elaboration
    0.75
    InSection
    0.71
     refinement
    0.70
    WriteBarrier
    0.70
    __*/
    0.68
    Activations Density 0.095%

    No Known Activations