© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 54534
    Prev
    Next
    INDEX
    Explanations

    aspects related to the quality and characteristics of food, service, and ambiance in restaurant reviews

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

    describing aspects of experiences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.82
     Infórmanos
    -0.73
     الرياضيه
    -0.70
    RTEE
    -0.69
    costal
    -0.69
    niſſe
    -0.68
     Савезне
    -0.66
     HttpNotFound
    -0.66
     Biôgrafia
    -0.65
    [@BOS@]
    -0.64
    POSITIVE LOGITS
    AxisAlignment
    0.34
     suena
    0.31
    AutoScaleMode
    0.30
     is
    0.28
    cessite
    0.28
     sufrido
    0.28
    couvrez
    0.27
     fréqu
    0.27
     esfuer
    0.26
     was
    0.26
    Activations Density 0.018%

    No Known Activations