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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15750
    Prev
    Next
    INDEX
    Explanations

    terms related to business phone usage and etiquette.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    words and phrases related to phone calls and communication devices.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    phrases related to cell phone etiquette and best practices in professional settings.

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

    answering phone calls/voicemails

    np_acts-logits-general · gemini-2.0-flash

    phone calls and messages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    FailureListener
    -0.57
    WebElementEntity
    -0.57
    IntoConstraints
    -0.56
    |()
    -0.55
    pexpr
    -0.54
     Observation
    -0.53
    lato
    -0.53
    dfunding
    -0.52
    ArgumentParser
    -0.51
    propTypes
    -0.51
    POSITIVE LOGITS
     answering
    1.09
     caller
    1.04
     answered
    1.03
     voicemail
    0.98
     callers
    0.95
     répon
    0.94
     answer
    0.89
     Answering
    0.89
     Caller
    0.89
    answered
    0.86
    Activations Density 0.144%

    No Known Activations