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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4698
    Prev
    Next
    INDEX
    Explanations

    positive sentiments or affirmations

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

    The plus sign

    np_acts-logits-general · gemini-2.0-flash

    math expressions and code separators

    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
    IUrlHelper
    -0.49
    RTEE
    -0.49
    AISSEE
    -0.44
     sellado
    -0.44
     asamblea
    -0.42
    writeFieldEnd
    -0.42
     TextFormField
    -0.42
     Akismet
    -0.41
    ه‌اند
    -0.41
     desmotivaciones
    -0.41
    POSITIVE LOGITS
    ++++++++++++++++
    0.82
    _+
    0.77
    ++++
    0.74
     +
    0.73
    +++
    0.72
    +++++
    0.71
    &+
    0.70
    ++++++++
    0.66
    %+
    0.66
     +.
    0.65
    Activations Density 0.474%

    No Known Activations