© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 2408
    Prev
    Next
    INDEX
    Explanations

    references to knives and their usage

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

    knives and cutting

    np_acts-logits-general · gemini-2.0-flash

    knife

    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
     terecht
    -0.44
     North
    -0.43
     regional
    -0.41
     Regional
    -0.41
     West
    -0.39
     Western
    -0.39
     Eastern
    -0.39
     N
    -0.39
     timp
    -0.38
     Northern
    -0.38
    POSITIVE LOGITS
    Knife
    0.93
     Towel
    0.92
     knife
    0.90
     toalla
    0.88
     Knife
    0.88
     towel
    0.85
    Candle
    0.85
     candle
    0.83
    knife
    0.81
    ucksack
    0.81
    Activations Density 0.716%

    No Known Activations