© 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. 11187
    Prev
    Next
    INDEX
    Explanations

    concepts related to relationships, distinctions, and comparisons in various contexts

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

    appearing before "of," "to," "the," or "this"

    np_acts-logits-general · gemini-2.0-flash

    of and between

    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
    rungsseite
    -0.73
    MessageOf
    -0.64
     AppCompatTheme
    -0.61
    SourceChecksum
    -0.60
     Taktlose
    -0.58
     protoimpl
    -0.57
    はじめに
    -0.56
    WithIOException
    -0.55
    DockStyle
    -0.54
    GeneratedMessage
    -0.54
    POSITIVE LOGITS
    AndFlush
    0.32
     secoli
    0.30
     dagar
    0.30
     doccia
    0.28
     дописавши
    0.28
     sensazione
    0.28
    tadır
    0.28
     Bourgoin
    0.28
     is
    0.28
     venner
    0.27
    Activations Density 1.919%

    No Known Activations