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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 1440
    Prev
    Next
    INDEX
    Explanations

    references to private entities and individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     onOptions
    -0.83
    GEBURTS
    -0.80
     épis
    -0.79
     duquel
    -0.71
     ThemeData
    -0.70
     obé
    -0.68
     HttpHeaders
    -0.68
    Sébastien
    -0.68
     Certifications
    -0.67
     cref
    -0.67
    POSITIVE LOGITS
     private
    1.49
     Private
    1.47
    Private
    1.44
    PRIVATE
    1.40
     PRIVATE
    1.32
    private
    1.25
     privada
    1.19
     privately
    1.18
     privat
    1.16
     Privat
    1.14
    Activations Density 0.054%

    No Known Activations