© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 1927
    Prev
    Next
    INDEX
    Explanations

    keywords associated with programming access modifiers and keywords in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     eliminación
    -0.37
     Garantía
    -0.35
    åringen
    -0.33
     conversión
    -0.32
     normalidad
    -0.31
     Potencia
    -0.31
     procès
    -0.31
     дії
    -0.30
    ientôt
    -0.30
     decimos
    -0.29
    POSITIVE LOGITS
    public
    1.27
     public
    1.02
     Public
    0.99
    Public
    0.97
    PUBLIC
    0.88
    IBOutlet
    0.85
     PUBLIC
    0.85
     تضيفلها
    0.84
     publick
    0.81
    󠁮
    0.81
    Activations Density 0.045%

    No Known Activations