© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 10739
    Prev
    Next
    INDEX
    Explanations

    specific character patterns or phonetic structures in words and phrases

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

    ending in "ee," "oo," or starting with "B"

    np_acts-logits-general · gemini-2.0-flash

    sounds or rhyming words

    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
     Wharton
    -0.47
     eiland
    -0.47
    mantec
    -0.44
    mfenced
    -0.44
    nteral
    -0.44
     Ralf
    -0.42
    vertx
    -0.41
     }],
    -0.41
     Lamont
    -0.41
     Walther
    -0.41
    POSITIVE LOGITS
    oo
    1.06
    Bee
    1.02
    lee
    1.02
    boo
    1.00
    bee
    0.98
    Boo
    0.96
     Bee
    0.94
    Doo
    0.93
     Coo
    0.93
    Moo
    0.93
    Activations Density 0.825%

    No Known Activations