© 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. 8818
    Prev
    Next
    INDEX
    Explanations

    sections of text with non-zero activations indicating significant emphasis or critical information missing from the content

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

    Text within square brackets

    np_acts-logits-general · gemini-2.0-flash

    numbers in brackets

    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
    Šaltiniai
    -0.64
    Voci
    -0.61
     eleg
    -0.59
    BindingResult
    -0.59
    RuleContext
    -0.59
    VStack
    -0.57
     pinulongan
    -0.57
    SequentialGroup
    -0.56
    basicConfig
    -0.56
    featureID
    -0.56
    POSITIVE LOGITS
     متعلقه
    0.67
     дописавши
    0.54
    évaluateur
    0.52
     "..\..\..\
    0.52
     doi
    0.50
    EndInit
    0.50
     Forth
    0.49
    存于互联网档案馆
    0.48
     Walkover
    0.48
     ital
    0.47
    Activations Density 0.097%

    No Known Activations