© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 6881
    Prev
    Next
    INDEX
    Explanations

    references to Android development components and their versions

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

    Colons and version numbers

    np_acts-logits-general · gemini-2.0-flash

    future forecasting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ImageContext
    -0.80
    HandlerContext
    -0.65
     @}
    -0.62
    mido
    -0.59
    Obrigado
    -0.56
    dafx
    -0.55
    PropertyGroup
    -0.54
     промо
    -0.53
    riwal
    -0.52
    MENAFN
    -0.52
    POSITIVE LOGITS
     BoxDecoration
    0.59
     تضيفلها
    0.55
     للمعارف
    0.54
     InputDecoration
    0.52
    FontOfSize
    0.52
     Supporters
    0.51
    ArgsConstructor
    0.50
     shui
    0.48
    ніципа
    0.48
    πάρχ
    0.47
    Activations Density 0.017%

    No Known Activations