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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 12-GEMMASCOPE-RES-16K
    6. 2084
    Prev
    Next
    INDEX
    Explanations

    named entities, particularly names of individuals or organizations

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

    elements related to Android layout attributes and settings.

    oai_token-act-pair · gpt-4oTriggered by @pigeonzow
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ...
    -0.56
     [
    -0.50
    ..
    -0.46
    1
    -0.46
    …
    -0.45
     án
    -0.45
     Angew
    -0.44
    2
    -0.43
    [
    -0.43
    cookieParser
    -0.42
    POSITIVE LOGITS
     समीक्षाओं
    0.93
    хьтан
    0.83
    Personendaten
    0.83
    ArrowToggle
    0.81
     ویکی‌پدی
    0.80
    Personensuche
    0.79
    évaluateur
    0.79
     дописавши
    0.79
    GEBURTSDATUM
    0.79
    Portale
    0.78
    Activations Density 0.202%

    No Known Activations