© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 8348
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions related to probability distributions and matrices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     réception
    -0.45
     Mon
    -0.42
     direct
    -0.41
    Mon
    -0.41
     directly
    -0.41
    remoto
    -0.40
    ourke
    -0.40
    ഴ
    -0.40
    athen
    -0.40
     받
    -0.40
    POSITIVE LOGITS
    __':
    
    0.88
    __":
    
    0.83
     betweenstory
    0.83
    __':
    0.79
    __":
    0.79
    EndGlobalSection
    0.78
    تقاوى
    0.76
    Hochspringen
    0.75
    IBOutlet
    0.72
    Personendaten
    0.71
    Activations Density 0.783%

    No Known Activations