© 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. 8082
    Prev
    Next
    INDEX
    Explanations

    expressions of something being enjoyable or impressive

    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
     useState
    -0.44
    iorno
    -0.35
     relationship
    -0.34
     segi
    -0.34
    ChildScrollView
    -0.33
     intention
    -0.31
    ệc
    -0.31
     приходится
    -0.30
     createSlice
    -0.30
     saumon
    -0.29
    POSITIVE LOGITS
     cool
    4.41
     Cool
    4.06
    Cool
    4.00
    cool
    3.81
     COOL
    3.64
    COOL
    3.34
     coolness
    3.25
     coolest
    3.16
     cools
    3.16
     cooler
    2.98
    Activations Density 0.063%

    No Known Activations