© 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. 20-GEMMASCOPE-RES-16K
    6. 16252
    Prev
    Next
    INDEX
    Explanations

    mentions of phones and phone-related communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mistura
    -0.45
    rets
    -0.42
     Magi
    -0.41
     kapit
    -0.41
    >]
    -0.41
    endwhile
    -0.41
     West
    -0.40
    rising
    -0.39
    guous
    -0.39
    makeConstraints
    -0.39
    POSITIVE LOGITS
    Phone
    1.41
     Phone
    1.34
     phone
    1.34
     PHONE
    1.29
    phone
    1.23
    getPhone
    1.22
    Telefon
    1.18
     Telephone
    1.14
    PHONE
    1.10
    Telephone
    1.09
    Activations Density 0.047%

    No Known Activations