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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 6783
    Prev
    Next
    INDEX
    Explanations

    terms related to topological insulators and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Topological insulators

    np_acts-logits-general · gemini-2.0-flash

    topological insulators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 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
    UnsafeEnabled
    -0.57
    หวัด
    -0.48
    hassee
    -0.48
     ſtand
    -0.47
    onomía
    -0.47
    Observed
    -0.46
    MessageState
    -0.45
    QMetaType
    -0.45
     kacang
    -0.45
     cauſe
    -0.45
    POSITIVE LOGITS
     topological
    0.33
    舺
    0.32
    windowFixed
    0.32
    ("")]
    
    0.31
    inflate
    0.31
    íng
    0.30
     يتيمه
    0.29
    Género
    0.29
     Lancet
    0.29
     tunneling
    0.29
    Activations Density 1.558%

    No Known Activations