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. 122798
    Prev
    Next
    INDEX
    Explanations

    the word "as" used in various contexts

    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
     becauſe
    -0.57
     ſta
    -0.56
    ########.
    -0.56
     ſtill
    -0.54
     Majefty
    -0.54
     myſelf
    -0.53
     abſ
    -0.52
     Winaray
    -0.52
     ſal
    -0.52
     Reſ
    -0.52
    POSITIVE LOGITS
     astore
    0.66
    PyExc
    0.46
    asList
    0.46
    UnsafeEnabled
    0.44
     мәкал
    0.43
     Adam
    0.42
    Personendaten
    0.41
     Harms
    0.40
    errHandler
    0.39
    MigrationBuilder
    0.38
    Activations Density 0.002%

    No Known Activations