© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 8161
    Prev
    Next
    INDEX
    Explanations

    instances of output statements in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/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.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     flexibilidad
    -0.62
     autonomía
    -0.59
     profesión
    -0.58
     productividad
    -0.53
     hipótesis
    -0.53
     creatividad
    -0.52
     instrucción
    -0.52
     comodidad
    -0.51
     restauración
    -0.51
     eficiencia
    -0.50
    POSITIVE LOGITS
     ſind
    0.71
     Houſe
    0.70
     Ly
    0.64
     utafitiHapana
    0.63
     Infórmanos
    0.63
     препратки
    0.61
     nob
    0.59
    TEMPO
    0.59
     WebDriverWait
    0.58
     press
    0.57
    Activations Density 0.647%

    No Known Activations