© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 8557
    Prev
    Next
    INDEX
    Explanations

    phrases indicating consistency in research or findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     secuencia
    -0.46
     gancho
    -0.44
     idées
    -0.44
     suena
    -0.44
     caminhão
    -0.44
     nación
    -0.44
     pleaſure
    -0.43
     competición
    -0.43
     Infór
    -0.41
     idéia
    -0.41
    POSITIVE LOGITS
     consistency
    1.03
     Consistency
    1.00
     consistent
    0.98
    consistent
    0.96
     consist
    0.94
    consistency
    0.93
    Consistency
    0.92
     Consistent
    0.88
    Consistent
    0.82
     inconsistent
    0.79
    Activations Density 0.441%

    No Known Activations