© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 4340
    Prev
    Next
    INDEX
    Explanations

    references to water and its various states and conditions

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

    Follows "was" or "is"

    np_acts-logits-general · gemini-2.0-flash

    is/was followed by a verb

    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
    Filled
    -0.37
    studded
    -0.36
     vazio
    -0.35
    oł
    -0.34
     filled
    -0.34
     zalo
    -0.34
     cerrada
    -0.32
    ţ
    -0.32
    ectomy
    -0.32
    GTCX
    -0.32
    POSITIVE LOGITS
     plentiful
    0.65
    Personensuche
    0.63
     Biôgrafia
    0.57
    tanleria
    0.56
     abundant
    0.56
     '\\;'
    0.55
     поступа
    0.54
     stored
    0.53
    GOTREF
    0.53
     spilled
    0.53
    Activations Density 0.886%

    No Known Activations