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. 4158
    Prev
    Next
    INDEX
    Explanations

    phrases indicating conclusions or deductions

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

    "we" followed by certain verbs

    np_acts-logits-general · gemini-2.0-flash

    we conclude or deduce

    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
    OGND
    -0.69
    mml
    -0.54
     loài
    -0.49
    CurrentValue
    -0.49
    PagerAdapter
    -0.48
     earners
    -0.48
    acamata
    -0.47
     Containing
    -0.46
     ό
    -0.46
    AttributeSet
    -0.46
    POSITIVE LOGITS
    #+#
    0.66
    DockStyle
    0.64
    __*/
    0.62
    Viitteet
    0.60
    nshaw
    0.58
    הערות
    0.58
    CppCodeGen
    0.57
     بيها
    0.55
     سكانية
    0.55
    ējās
    0.55
    Activations Density 0.394%

    No Known Activations