© 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. 0-GEMMASCOPE-RES-16K
    6. 3256
    Prev
    Next
    INDEX
    Explanations

    terms related to adequacy or sufficiency in various contexts

    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
     praça
    -0.40
     redacción
    -0.40
     нав
    -0.39
     beira
    -0.39
     difusión
    -0.39
     bahía
    -0.37
     autorité
    -0.36
     meditación
    -0.35
     invierno
    -0.35
     espectáculos
    -0.35
    POSITIVE LOGITS
    Autoritní
    0.80
     Propor
    0.79
    
    0.78
     Transformer
    0.76
    proportion
    0.75
    hollow
    0.74
     transformer
    0.74
     proportional
    0.73
    Hentet
    0.73
    propor
    0.72
    Activations Density 0.273%

    No Known Activations