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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3730
    Prev
    Next
    INDEX
    Explanations

    references to SMS and text messaging

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

    SMS and text messaging

    np_acts-logits-general · gemini-2.0-flash

    SMS text messages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     houſe
    -0.54
     ſur
    -0.54
     raiſ
    -0.53
     Houſe
    -0.52
    ſelf
    -0.52
     ſta
    -0.51
     ſel
    -0.49
    Tembelea
    -0.49
     faſt
    -0.48
     paſſ
    -0.46
    POSITIVE LOGITS
     SMS
    0.79
     sms
    0.79
    SMS
    0.73
    短信
    0.68
     texted
    0.67
    Sms
    0.63
    sms
    0.62
     texting
    0.60
     Sms
    0.57
    RenderAtEndOf
    0.49
    Activations Density 0.151%

    No Known Activations