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. 15315
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notation related to statistical measures

    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
     protoimpl
    -0.61
    tagHelperRunner
    -0.59
    extAlignment
    -0.52
    webElementXpaths
    -0.50
     @"/
    -0.49
    nodoc
    -0.47
    Vidite
    -0.46
    expandindo
    -0.46
    pushFollow
    -0.46
    DockStyle
    -0.45
    POSITIVE LOGITS
    новништво
    0.49
     sebaliknya
    0.39
     Organizador
    0.37
    styleUrls
    0.37
     oreja
    0.36
    ńcu
    0.36
    ⤹
    0.36
    jería
    0.36
    selben
    0.36
     Bemerkungen
    0.35
    Activations Density 1.856%

    No Known Activations