© 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. 15-GEMMASCOPE-RES-16K
    6. 1445
    Prev
    Next
    INDEX
    Explanations

    instances of the word "represent" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rotina
    -0.57
    Quick
    -0.52
    Redacción
    -0.50
     Duplex
    -0.49
     Pakai
    -0.48
    Zü
    -0.48
    Married
    -0.47
    Drill
    -0.46
    Criminal
    -0.46
    Powder
    -0.46
    POSITIVE LOGITS
     representation
    1.34
     Represent
    1.34
     represent
    1.33
     REPRESENT
    1.28
     represents
    1.23
    represent
    1.23
     representing
    1.22
    Represent
    1.20
     Representation
    1.15
    representation
    1.12
    Activations Density 0.267%

    No Known Activations