© 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. 16-GEMMASCOPE-RES-16K
    6. 8013
    Prev
    Next
    INDEX
    Explanations

    code snippets related to variable packing and type checking in programming

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

    Data types: Sfixed, Sint, Fixed

    np_acts-logits-general · gemini-2.0-flash

    signed fixed integers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ixen
    -0.51
     Italijani
    -0.50
     InputDecoration
    -0.48
    ueira
    -0.48
    GroupBy
    -0.48
     forder
    -0.46
     کنی
    -0.46
     drill
    -0.46
    出版年
    -0.45
     незавершена
    -0.45
    POSITIVE LOGITS
     виправивши
    0.70
     PyLong
    0.63
    SIGNED
    0.63
    Signed
    0.56
     casting
    0.56
     precision
    0.55
     signed
    0.55
     configureStore
    0.55
     overflows
    0.54
    precision
    0.53
    Activations Density 0.703%

    No Known Activations