© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 4628
    Prev
    Next
    INDEX
    Explanations

    words or phrases that denote belonging or possession

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

    Preposition "of" followed by a word

    np_acts-logits-general · gemini-2.0-flash

    'of' followed by another word

    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
     preferred
    -0.57
     preference
    -0.54
     SqlCommand
    -0.53
     Preference
    -0.52
    writeFieldEnd
    -0.52
     disambiguazione
    -0.51
    Distribuzione
    -0.50
    ConstraintMaker
    -0.50
    moveToFirst
    -0.50
    BeginContext
    -0.49
    POSITIVE LOGITS
     them
    0.42
    uarkan
    0.40
    脚注の使い方
    0.39
    íes
    0.38
     Schie
    0.37
     GenerationType
    0.37
    bulkan
    0.35
     NUKAT
    0.33
    當然
    0.33
     sejauh
    0.33
    Activations Density 0.093%

    No Known Activations