© 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. 2-GEMMASCOPE-RES-16K
    11. 13134
    Prev
    Next
    INDEX
    Explanations

    issues or references related to encoding formats, particularly UTF

    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
     Perſ
    -0.48
     Schub
    -0.45
     Chapin
    -0.43
    nungszeiten
    -0.42
     pecuni
    -0.41
     Distrikt
    -0.41
    noty
    -0.40
     favorita
    -0.40
    stateMutability
    -0.39
    setSelection
    -0.39
    POSITIVE LOGITS
    HtmlAttribute
    0.68
    utf
    0.59
     mum
    0.59
     Mum
    0.57
    Mum
    0.56
     Beef
    0.55
    Jeografia
    0.54
    AndEndTag
    0.50
     Syria
    0.49
     FetchType
    0.49
    Activations Density 0.485%

    No Known Activations