Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 6302
    Prev
    Next
    INDEX
    Explanations

    references to corporate entities and financial transactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ujednoznacz
    -0.50
     يتيمه
    -0.50
     disambiguazione
    -0.48
    ResponseWriter
    -0.47
    SuppressLint
    -0.47
     simplifié
    -0.43
     חיצוניים
    -0.42
    RegressionTest
    -0.42
    令和
    -0.41
     урна
    -0.41
    POSITIVE LOGITS
     company
    0.58
     compañía
    0.56
    ſelf
    0.56
     Majefty
    0.55
     Houſe
    0.53
     armée
    0.52
     companies
    0.52
     Company
    0.50
     Chriftian
    0.50
    集團
    0.49
    Activations Density 0.665%

    No Known Activations