© 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-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 8220
    Prev
    Next
    INDEX
    Explanations

    references to chemical compounds and their concentrations in scientific contexts

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

    Numbers after apostrophes/primes

    np_acts-logits-general · gemini-2.0-flash

    numbers and measurements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fellowship
    -0.50
    MENAFN
    -0.49
    REJECT
    -0.47
     Zust
    -0.46
     fellowship
    -0.45
    istema
    -0.44
    चे
    -0.44
    Trans
    -0.43
    lığ
    -0.43
     kepem
    -0.43
    POSITIVE LOGITS
    IUrlHelper
    0.73
    httphttps
    0.70
    HtmlAttribute
    0.68
    styleType
    0.60
     للمعارف
    0.59
    ReusableCell
    0.58
    richTextPanel
    0.58
     typelib
    0.57
     Савезне
    0.56
     ProtoMessage
    0.56
    Activations Density 1.654%

    No Known Activations