© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 5768
    Prev
    Next
    INDEX
    Explanations

    various food ingredients and their combinations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Orlando
    -0.38
     Orlando
    -0.35
    Inter
    -0.35
    LayoutConstraint
    -0.34
    Билгалдахарш
    -0.34
    QObject
    -0.33
     pat
    -0.33
    SerializedName
    -0.32
    INSTR
    -0.32
     Bho
    -0.32
    POSITIVE LOGITS
     asparagus
    1.25
     onion
    1.23
     barley
    1.18
     broccoli
    1.16
     onions
    1.13
     lettuce
    1.11
     Asparagus
    1.10
     alfalfa
    1.09
     wheat
    1.08
     spinach
    1.07
    Activations Density 1.665%

    No Known Activations