© 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. 2-GEMMASCOPE-RES-16K
    6. 3521
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the absence of something or lack of specific conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelper
    -0.56
     jSON
    -0.54
    toJSONString
    -0.54
    PerformLayout
    -0.52
     ſtate
    -0.52
    SerializedSize
    -0.50
     purpoſe
    -0.49
    näm
    -0.48
    ugc
    -0.48
     Majefty
    -0.46
    POSITIVE LOGITS
     without
    3.72
    without
    3.39
     Without
    3.38
    Without
    3.33
     WITHOUT
    3.02
    WITHOUT
    2.86
     zonder
    2.81
     без
    2.80
     ohne
    2.77
     tanpa
    2.66
    Activations Density 0.157%

    No Known Activations