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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 11893
    Prev
    Next
    INDEX
    Explanations

    financial and mathematical terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.36
     sensación
    -0.34
     concevoir
    -0.33
     kesan
    -0.32
    лючение
    -0.32
    ThemeOverlay
    -0.31
     transfé
    -0.31
     EXAMIN
    -0.31
     šķ
    -0.29
     conduire
    -0.29
    POSITIVE LOGITS
    IndentedString
    0.60
    Portale
    0.57
     plus
    0.56
     دیکھیے
    0.53
    __':
    
    0.53
    WebServlet
    0.53
    ագրություններ
    0.52
    LEncoder
    0.52
    رشف
    0.51
    FunctionFlags
    0.51
    Activations Density 1.627%

    No Known Activations