© 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-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 16196
    Prev
    Next
    INDEX
    Explanations

    messages related to errors and failures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Sucesor
    -0.53
     okuyayım
    -0.51
    RuleContext
    -0.48
     समीक्षाएं
    -0.48
    MergeFrom
    -0.46
    UnusedPrivate
    -0.45
    EndGlobalSection
    -0.44
    oredCriteria
    -0.44
     autorytatywna
    -0.43
    }])
    -0.43
    POSITIVE LOGITS
     Something
    0.96
     something
    0.94
    Something
    0.94
    something
    0.86
     SOMETHING
    0.83
     unable
    0.77
    ficulty
    0.77
     trouble
    0.73
    unable
    0.72
     Unable
    0.72
    Activations Density 0.116%

    No Known Activations