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. 3133
    Prev
    Next
    INDEX
    Explanations

    names and titles associated with individuals

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

    after names ending in "-Guzman" or "Gomez"

    np_acts-logits-general · gemini-2.0-flash

    names and surnames

    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
     noires
    -0.86
     étoit
    -0.80
     auroit
    -0.80
     avoient
    -0.79
     poffible
    -0.75
     pouvoit
    -0.72
     Darío
    -0.71
     Mercurio
    -0.70
    TypedDataSet
    -0.69
    cherichia
    -0.69
    POSITIVE LOGITS
     de
    0.75
     y
    0.61
    Personendaten
    0.57
     del
    0.52
     Zub
    0.52
     River
    0.51
     Pastor
    0.50
     Men
    0.50
     Mel
    0.48
     Mart
    0.47
    Activations Density 0.268%

    No Known Activations