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
    4. Residual Stream - 131k
    5. 24-GEMMASCOPE-RES-131K
    6. 1175
    Prev
    Next
    INDEX
    Explanations

    HTML button elements and their related attributes

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

    HTML tag endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.65
     NSCoder
    -0.63
     Мексичка
    -0.61
    bootstrapcdn
    -0.59
    下载附件
    -0.58
     Normdatei
    -0.58
    
    -0.56
    CppCodeGen
    -0.56
    printStackTrace
    -0.54
     silos
    -0.54
    POSITIVE LOGITS
    UnusedPrivate
    0.36
     alternativo
    0.36
     Monark
    0.35
     Procu
    0.35
     قرار
    0.32
     Gleichzeitig
    0.32
     parcial
    0.30
     Alternative
    0.30
    nocześnie
    0.30
    Alternative
    0.30
    Activations Density 0.006%

    No Known Activations