Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 6240
    Prev
    Next
    INDEX
    Explanations

    repeated instances of the word "go."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    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
    -0.72
    MemoryWarning
    -0.72
     itſelf
    -0.69
    AndEndTag
    -0.67
     myſelf
    -0.64
     fubject
    -0.64
     sonnen
    -0.62
     houſe
    -0.62
     reaſon
    -0.62
    amitié
    -0.61
    POSITIVE LOGITS
     go
    3.40
     goes
    3.32
    goes
    2.63
     Goes
    2.63
    go
    2.54
    Go
    2.52
     went
    2.48
     Go
    2.48
    Goes
    2.47
     going
    2.46
    Activations Density 0.073%

    No Known Activations