© 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. 8938
    Prev
    Next
    INDEX
    Explanations

    references to attributes or characteristics, particularly in relation to ADHD and its impact

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

    Code, law, or opinion mentioning "Att" or "attr"

    np_acts-logits-general · gemini-2.0-flash

    attending, attribute, attorney, attrgetter

    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
    MemoryWarning
    -0.93
    AddTagHelper
    -0.87
    webElementXpaths
    -0.78
     propOrder
    -0.78
    MethodManager
    -0.73
     requestCode
    -0.70
    ModelForm
    -0.69
     Füße
    -0.69
    ModelSerializer
    -0.67
     jLabel
    -0.67
    POSITIVE LOGITS
     Att
    0.88
     AttributeSet
    0.87
     attr
    0.85
     attrs
    0.84
     ATT
    0.79
    attrs
    0.77
    addAttribute
    0.75
    attr
    0.74
    Ath
    0.72
     Atta
    0.72
    Activations Density 0.301%

    No Known Activations