© 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. 5028
    Prev
    Next
    INDEX
    Explanations

    key phrases related to quantities and accommodations

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

    Expressing or implying that something is sufficient

    np_acts-logits-general · gemini-2.0-flash

    sufficiency and capacity

    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
    msgid
    -0.30
     culture
    -0.28
     u
    -0.27
     культура
    -0.27
     band
    -0.26
    getStatusCode
    -0.25
     Ver
    -0.24
    AccessControl
    -0.24
     l
    -0.23
     signal
    -0.23
    POSITIVE LOGITS
    enough
    1.05
     enough
    1.05
     Enough
    1.01
    Enough
    1.01
     sufficient
    0.94
     accommodates
    0.93
     Sufficient
    0.90
     suficiente
    0.89
    Sufficient
    0.85
     ENOUGH
    0.85
    Activations Density 0.185%

    No Known Activations