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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 13032
    Prev
    Next
    INDEX
    Explanations

    references to leaving messages, particularly in a communication context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Leaving a message

    np_acts-logits-general · gemini-2.0-flash

    leave a message or voicemail

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     гори
    -0.51
    ViewFeatures
    -0.49
    ￡
    -0.48
     denominator
    -0.48
    toch
    -0.46
     consultato
    -0.46
    Unnamed
    -0.45
     praça
    -0.45
    اق
    -0.44
    tifiable
    -0.44
    POSITIVE LOGITS
     message
    1.86
    message
    1.61
     messages
    1.60
     Message
    1.52
     MESSAGE
    1.36
     mensaje
    1.35
    Message
    1.34
     msg
    1.32
     Messages
    1.31
    MESSAGE
    1.22
    Activations Density 0.157%

    No Known Activations