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 - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 2028
    Prev
    Next
    INDEX
    Explanations

    sections of text with specific structured information, such as questions and answers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    دانشنامهٔ
    -0.71
     باخ
    -0.59
    Diweddarwch
    -0.56
    المشاركات
    -0.56
    تقاوى
    -0.55
     unknownFields
    -0.54
    NameInMap
    -0.53
    DockStyle
    -0.52
     فريبيس
    -0.52
    hoeddwyd
    -0.52
    POSITIVE LOGITS
     Berikut
    0.45
     folgender
    0.39
     Explanation
    0.39
     exp
    0.38
    Explanation
    0.36
     explained
    0.36
    Exp
    0.35
     içeri
    0.35
     Below
    0.35
     explains
    0.35
    Activations Density 0.897%

    No Known Activations