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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 126475
    Prev
    Next
    INDEX
    Explanations

    phrases related to dietary preferences and medical directives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ynchronously
    -0.48
     contextLoads
    -0.45
    aderie
    -0.44
    richTextPanel
    -0.42
    tifacts
    -0.41
    Hochspringen
    -0.40
    发表于
    -0.39
    ClientRect
    -0.38
    \{\\
    -0.37
    DockStyle
    -0.37
    POSITIVE LOGITS
     request
    0.45
     requesting
    0.42
    lieben
    0.42
     gyhoeddwyd
    0.42
    Hentet
    0.41
    ۜ
    0.41
     orders
    0.41
    Request
    0.40
    Dry
    0.39
    TintMode
    0.39
    Activations Density 0.012%

    No Known Activations