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. 20-GEMMASCOPE-RES-131K
    6. 114896
    Prev
    Next
    INDEX
    Explanations

    lines of code defining constants or functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    NameInMap
    -0.54
    CodeAttribute
    -0.42
     OFDb
    -0.41
    '}),
    -0.41
    "]]
    -0.40
    <bos>
    -0.40
    ']]
    -0.38
    ']),
    -0.37
     Schluß
    -0.36
     pulumi
    -0.36
    POSITIVE LOGITS
     NSCoder
    0.62
    KURZBESCHREIBUNG
    0.58
    MemoryWarning
    0.55
     intptr
    0.55
    BagLayout
    0.54
    VersionUID
    0.54
     BrowserModule
    0.54
     Vikipedi
    0.50
    rungsseite
    0.50
    dafx
    0.47
    Activations Density 0.001%

    No Known Activations