© 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-2-2B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 13855
    Prev
    Next
    INDEX
    Explanations

    various metrics and scores, particularly those assessing performance or evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     terciopelo
    -0.67
     препратки
    -0.66
    isnan
    -0.65
     hinein
    -0.65
    Gweler
    -0.65
    zewod
    -0.65
     ostavi
    -0.65
     embora
    -0.64
    Outlined
    -0.64
    umumkan
    -0.63
    POSITIVE LOGITS
     scores
    1.54
     Scores
    1.47
     scored
    1.38
     score
    1.35
    Scores
    1.27
     Score
    1.25
     scoring
    1.25
    scores
    1.24
     SCORE
    1.23
     scorer
    1.18
    Activations Density 0.074%

    No Known Activations