© 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. 4251
    Prev
    Next
    INDEX
    Explanations

    elements of dialogue and conversational structure within the text

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

    a pause or break in a narrative

    np_acts-logits-general · gemini-2.0-flash

    But I, })\psi, toy construction

    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
    новништво
    -0.58
    期刊论文
    -0.46
     Lokales
    -0.46
     ویکی‌پدی
    -0.45
     InputDecoration
    -0.44
    󠁣
    -0.43
    MessageOf
    -0.43
     StatelessWidget
    -0.43
    TintMode
    -0.42
     EconPapers
    -0.41
    POSITIVE LOGITS
     meanwhile
    1.15
     meantime
    1.12
     Meanwhile
    0.93
     Until
    0.90
    Meanwhile
    0.90
    Until
    0.88
     until
    0.84
     frattempo
    0.72
     interim
    0.72
    お楽しみに
    0.69
    Activations Density 0.317%

    No Known Activations