© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 5424
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "txt" and related UI component identifiers in code or text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.73
    MLLoader
    -0.65
     विश्वसनीयता
    -0.59
     SetUp
    -0.57
    ease
    -0.56
     Bees
    -0.55
     Biôgrafia
    -0.54
    elementType
    -0.53
    Portail
    -0.52
    bees
    -0.52
    POSITIVE LOGITS
    txt
    1.30
     txt
    1.20
    Txt
    1.02
     Txt
    0.91
    TXT
    0.89
    txtName
    0.75
     TXT
    0.67
     lbl
    0.56
    lbl
    0.55
    Johnny
    0.53
    Activations Density 0.157%

    No Known Activations