© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 81306
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and certain emotional sentiments expressed in the text

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

    text following punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     otomatig
    -0.51
     disambiguazione
    -0.47
     createSlice
    -0.41
    Filmografie
    -0.40
    Viited
    -0.40
    GIVEREF
    -0.40
    expandindo
    -0.38
    writeFieldEnd
    -0.38
    хьтан
    -0.38
     länder
    -0.36
    POSITIVE LOGITS
    Personendaten
    0.49
     IPT
    0.47
     hinweg
    0.46
    actus
    0.46
    achal
    0.46
    AVIS
    0.45
     ذا
    0.44
    cardinal
    0.44
     Adidas
    0.44
     gevo
    0.44
    Activations Density 0.087%

    No Known Activations