© 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. 34-GEMMASCOPE-RES-16K
    6. 11808
    Prev
    Next
    INDEX
    Explanations

    instances of the word "establish" and its variants in the context of forming foundations or confirming the existence of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     utafitiHapana
    -0.56
    ⓧ
    -0.51
     unknownFields
    -0.49
    parsedMessage
    -0.47
    oneofs
    -0.47
    ########.
    -0.47
    postsleuth
    -0.46
    Tembelea
    -0.46
     onOptions
    -0.45
    writeField
    -0.45
    POSITIVE LOGITS
     Establish
    0.65
     établie
    0.63
     establish
    0.63
     Establishing
    0.59
     establishes
    0.58
     ESTABL
    0.58
     Estab
    0.58
     established
    0.57
     Establishment
    0.57
    Establish
    0.57
    Activations Density 0.132%

    No Known Activations