© 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. 18-GEMMASCOPE-RES-16K
    11. 10712
    Prev
    Next
    INDEX
    Explanations

    specific forms and formats related to mailing addresses and checkboxes

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

    "checked the box" phrase

    np_acts-logits-general · gemini-2.0-flash

    checked the box

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     juſ
    -0.64
    IUrlHelper
    -0.64
     SafeMath
    -0.56
    InstanceState
    -0.55
     rencontr
    -0.55
     WaitForSeconds
    -0.55
     препратки
    -0.53
     reaſon
    -0.53
    titleMargin
    -0.52
    ✭✭
    -0.52
    POSITIVE LOGITS
     box
    2.04
     boxes
    1.81
     Box
    1.77
    box
    1.71
    Box
    1.65
     BOX
    1.57
    boxes
    1.56
    BOX
    1.49
     Boxes
    1.48
    Boxes
    1.36
    Activations Density 0.107%

    No Known Activations