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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 35-GEMMASCOPE-RES-16K
    6. 7050
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to federal housing regulations and procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WaitGroup
    -0.33
    INSEE
    -0.30
    nmgp
    -0.29
    Diwedd
    -0.28
    ExtendWith
    -0.27
     vois
    -0.26
    Insee
    -0.24
    UseVisualStyle
    -0.24
    opardy
    -0.23
     demos
    -0.23
    POSITIVE LOGITS
     guidelines
    1.63
     Guidelines
    1.55
    Guidelines
    1.43
     guideline
    1.42
     guidance
    1.39
    guidelines
    1.34
     Guideline
    1.34
     guide
    1.34
     Guide
    1.32
     Guidance
    1.30
    Activations Density 0.686%

    No Known Activations