© 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-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 10687
    Prev
    Next
    INDEX
    Explanations

    various forms of the letter 'e' and its associated patterns in the text

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

    Text fragments followed or preceded by specific punctuation marks

    np_acts-logits-general · gemini-2.0-flash

    conjunctions (and, 和, &)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omorphic
    -0.44
    ilistic
    -0.44
    XmlType
    -0.40
    initis
    -0.40
     ✭✭
    -0.40
     مرئيه
    -0.40
    󠁣
    -0.39
    idency
    -0.39
    tility
    -0.39
     EAR
    -0.39
    POSITIVE LOGITS
    webElementXpaths
    0.67
    力和
    0.66
    子和
    0.63
    和
    0.62
    人和
    0.61
    ﹠
    0.59
     And
    0.59
     AND
    0.59
     and
    0.59
     和
    0.55
    Activations Density 0.618%

    No Known Activations