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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 14351
    Prev
    Next
    INDEX
    Explanations

    HTML links related to technical specifications and documentation

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

    `.pdf">GLSL specification</a>, `https` links

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     GenerationType
    -0.55
    gatsby
    -0.43
    apimachinery
    -0.38
    exitRule
    -0.38
     المعيارى
    -0.37
     citoy
    -0.35
    ChildScrollView
    -0.34
     nera
    -0.32
    Autoritní
    -0.32
     mujer
    -0.31
    POSITIVE LOGITS
    httphttps
    0.61
    RTCK
    0.60
     мәкал
    0.57
    MemoryWarning
    0.57
     kasarigan
    0.53
    Panamoan
    0.52
    LookAnd
    0.51
    lovakia
    0.50
     Wikimedijinoj
    0.50
     Poehler
    0.50
    Activations Density 0.100%

    No Known Activations