© 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. 36-GEMMASCOPE-RES-16K
    6. 15939
    Prev
    Next
    INDEX
    Explanations

    elements associated with mechanical engineering and safety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tartalomajánló
    -0.37
    Diwedd
    -0.37
    findpost
    -0.36
    GEBURTSDATUM
    -0.36
    zsche
    -0.36
    DataAnnotations
    -0.35
     Bioaccumulative
    -0.35
     оригіналу
    -0.35
    étaro
    -0.34
     viewDidLoad
    -0.33
    POSITIVE LOGITS
     operation
    3.48
     oper
    3.16
     Operation
    3.08
    operation
    3.06
     operations
    3.00
     operate
    2.98
     operar
    2.94
    Operation
    2.92
     Oper
    2.86
     operating
    2.86
    Activations Density 1.056%

    No Known Activations