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. 105164
    Prev
    Next
    INDEX
    Explanations

    references to football statistics and records

    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
    もちゃ
    -0.46
    WithIOException
    -0.43
     nai
    -0.42
    cui
    -0.42
    Stere
    -0.42
     AppCompatTheme
    -0.41
     Taktlose
    -0.41
     Modèle
    -0.41
     strategically
    -0.41
    Svar
    -0.41
    POSITIVE LOGITS
    VersionUID
    0.46
    AndEndTag
    0.44
    Hentet
    0.42
    cookieParser
    0.39
    VolleyError
    0.38
    parsedMessage
    0.38
    IVEREF
    0.37
    ClientRect
    0.37
     المعيارى
    0.36
    地看着
    0.36
    Activations Density 0.013%

    No Known Activations