© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 14956
    Prev
    Next
    INDEX
    Explanations

    references to communication, especially regarding phone calls and requests for telephone access

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 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
    exitRule
    -0.63
     Roskov
    -0.54
    verwijspagina
    -0.54
     gawas
    -0.54
     Italijani
    -0.52
    SourceChecksum
    -0.52
    ➟
    -0.51
    TypedDataSet
    -0.51
    vels
    -0.51
     EconPapers
    -0.50
    POSITIVE LOGITS
     phone
    2.91
     call
    2.71
     telephone
    2.65
     calls
    2.51
     Phone
    2.40
    phone
    2.34
    call
    2.33
     PHONE
    2.32
    Phone
    2.30
     Call
    2.26
    Activations Density 0.393%

    No Known Activations