© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 3283
    Prev
    Next
    INDEX
    Explanations

    messages related to quality assurance and customer satisfaction guarantees

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

    Following punctuation related to contacting services

    np_acts-logits-general · gemini-2.0-flash

    contact or call

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esserung
    -0.44
    AsUp
    -0.44
    InsertCommand
    -0.43
    כב
    -0.43
    ására
    -0.43
    ')['
    -0.42
     diffuse
    -0.41
     Wikimedijinoj
    -0.40
     pos
    -0.40
    omenta
    -0.40
    POSITIVE LOGITS
     contact
    1.99
     Contact
    1.93
    Contact
    1.85
    contact
    1.78
     CONTACT
    1.69
    CONTACT
    1.55
     Call
    1.54
     call
    1.52
    Call
    1.49
     contacting
    1.44
    Activations Density 0.104%

    No Known Activations