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. 11-GEMMASCOPE-RES-16K
    6. 10087
    Prev
    Next
    INDEX
    Explanations

    references to specific aspects or features of various topics or subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.42
     Wikimedijinoj
    -0.42
     vermelhas
    -0.37
     shoes
    -0.36
     الرخصة
    -0.35
     book
    -0.34
     noDo
    -0.33
     institutions
    -0.33
     number
    -0.33
     devices
    -0.32
    POSITIVE LOGITS
     aspect
    1.30
     aspects
    1.30
    aspects
    1.29
     Aspects
    1.26
    Aspects
    1.20
    aspect
    1.18
     Aspect
    1.13
     aspek
    1.07
    Aspect
    1.01
     aspectos
    0.96
    Activations Density 0.240%

    No Known Activations