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-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8283
    Prev
    Next
    INDEX
    Explanations

    legal terms and phrases related to guidelines and conditions

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

    standards, guidelines, or specifications

    np_acts-logits-general · gemini-2.0-flash

    South Sudanese citizenship

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyTitle
    -0.51
    
    -0.45
    BASEPATH
    -0.44
    tra
    -0.43
     القدم
    -0.41
    ennis
    -0.41
     Kue
    -0.41
    KommentareTeilen
    -0.41
     Bag
    -0.40
    sizeCache
    -0.40
    POSITIVE LOGITS
     Obrador
    0.47
     modernas
    0.47
    sonaro
    0.45
    IUrlHelper
    0.44
    ranslated
    0.41
     recientemente
    0.41
    recently
    0.40
     nouveaux
    0.40
    Recently
    0.39
     reciente
    0.39
    Activations Density 0.862%

    No Known Activations