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. 8-GEMMASCOPE-RES-16K
    6. 300
    Prev
    Next
    INDEX
    Explanations

    references to white dwarf stars and their related properties and phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_8/width_16k/average_l0_99
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InitVars
    -0.51
    principalTable
    -0.46
    vismo
    -0.44
    AndEndTag
    -0.43
    MLLoader
    -0.40
     العنوان
    -0.40
    Crossref
    -0.40
    yı
    -0.39
    Aktualisiert
    -0.39
    tesi
    -0.39
    POSITIVE LOGITS
     dwarf
    0.54
     Dwarf
    0.54
     Dwar
    0.53
     diminutive
    0.53
     dwarfs
    0.52
     Photocase
    0.52
     gnome
    0.50
    dwarf
    0.49
    Dwarf
    0.48
     dwar
    0.48
    Activations Density 0.648%

    No Known Activations