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. 25-GEMMASCOPE-RES-16K
    6. 10225
    Prev
    Next
    INDEX
    Explanations

    quotations and speech markers in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    saraba
    -0.50
     &___
    -0.43
    NamedQueries
    -0.39
     ddelweddau
    -0.39
    WriteBarrier
    -0.36
    DrawerToggle
    -0.36
    SequentialGroup
    -0.36
    tanleria
    -0.35
    WithMany
    -0.34
    oneph
    -0.34
    POSITIVE LOGITS
    가
    0.57
    에
    0.56
    의
    0.55
    이
    0.54
    기
    0.54
    는
    0.52
    중
    0.52
    초
    0.52
    위
    0.52
    로
    0.52
    Activations Density 3.791%

    No Known Activations