Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 16280
    Prev
    Next
    INDEX
    Explanations

    descriptive attributes of food or beverages, particularly flavors and qualities of olive oil

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.48
    httphttps
    -0.46
    SceneManagement
    -0.44
    DataPropertyName
    -0.44
    tvguidetime
    -0.43
    bufio
    -0.42
    spesies
    -0.41
     combineReducers
    -0.40
     shipment
    -0.40
    ьаж
    -0.40
    POSITIVE LOGITS
     hints
    0.60
     notes
    0.59
    NameInMap
    0.55
     lingering
    0.54
     dominates
    0.54
    notes
    0.50
     dominating
    0.50
     lingers
    0.49
     Hints
    0.48
     vegetal
    0.48
    Activations Density 0.029%

    No Known Activations