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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 5748
    Prev
    Next
    INDEX
    Explanations

    references to making phone calls and communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     juges
    -0.31
     médié
    -0.31
     comporte
    -0.31
     visual
    -0.31
    gegen
    -0.30
    phosa
    -0.30
     hipster
    -0.29
     moyens
    -0.28
    ligg
    -0.28
     يتم
    -0.28
    POSITIVE LOGITS
    telephone
    0.93
     telef
    0.91
     telephone
    0.91
     telefon
    0.89
     Telephone
    0.87
     phone
    0.85
    電話
    0.82
    Telephone
    0.81
     telephones
    0.81
     telefono
    0.75
    Activations Density 0.181%

    No Known Activations