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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2101
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the positions and situations of individuals in a legal or organizational context

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

    surrounding "position" and "situation"

    np_acts-logits-general · gemini-2.0-flash

    position or situation

    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
     kasarigan
    -0.64
    setViewportView
    -0.57
    ecore
    -0.55
    MessageOf
    -0.54
    RegistryLite
    -0.53
     références
    -0.52
     nonatomic
    -0.51
    haupt
    -0.51
    keur
    -0.49
     doGet
    -0.49
    POSITIVE LOGITS
     position
    1.84
     situation
    1.69
     Position
    1.57
    position
    1.47
     POSITION
    1.44
    situation
    1.42
    Position
    1.39
     Situation
    1.35
     posición
    1.34
     situación
    1.31
    Activations Density 0.231%

    No Known Activations