© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 10773
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to various food items and culinary dishes

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

    preceding food names

    np_acts-logits-general · gemini-2.0-flash

    food descriptions

    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
    findpost
    -0.40
     dem
    -0.39
    Jedis
    -0.37
    MeasureSpec
    -0.36
     cooked
    -0.34
    ClInclude
    -0.34
     Budaya
    -0.33
    RegisterType
    -0.33
    ()>
    -0.33
     noodles
    -0.32
    POSITIVE LOGITS
    writeFieldEnd
    0.52
    detectChanges
    0.49
     recev
    0.48
    recrow
    0.47
    TargetException
    0.46
     tartalomajánló
    0.46
     GenerationType
    0.45
    XmlAccessType
    0.44
    ortage
    0.42
     dalamnya
    0.42
    Activations Density 0.192%

    No Known Activations