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. 13862
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and calculations

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

    Fractions

    np_acts-logits-general · gemini-2.0-flash

    mathematical fractions and calculations

    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
    +(
    -0.51
    AutoScaleMode
    -0.47
    ThemeOverlay
    -0.44
    ult
    -0.43
     Roskov
    -0.43
    se
    -0.42
    oa̍t
    -0.42
    ose
    -0.42
    less
    -0.42
    rasında
    -0.41
    POSITIVE LOGITS
    Datuak
    0.73
     يتيمه
    0.64
    ագրություններ
    0.61
    hyrchwyd
    0.61
    ecution
    0.60
    HomeAsUpEnabled
    0.59
     BorderRadius
    0.58
     Cister
    0.57
    raught
    0.56
    󠁿
    0.55
    Activations Density 1.757%

    No Known Activations