Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 12760
    Prev
    Next
    INDEX
    Explanations

    references to financial products and services

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

    after "to" or "at"

    np_acts-logits-general · gemini-2.0-flash

    sitting at, talk about, my feeling

    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
     M
    -0.51
    APORE
    -0.50
    randomUUID
    -0.49
    Whilst
    -0.48
     (
    -0.47
    ţi
    -0.47
    itzende
    -0.46
     K
    -0.44
    (
    -0.44
    POSITIVE LOGITS
    +#+#
    0.84
    Personendaten
    0.84
     Administrativna
    0.76
    Rhestr
    0.73
     تضيفلها
    0.72
    rungsseite
    0.71
    GEBURTSDATUM
    0.70
     مشين
    0.69
     Проци
    0.67
     ComVisible
    0.67
    Activations Density 0.213%

    No Known Activations