© 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. 11041
    Prev
    Next
    INDEX
    Explanations

    questions and inquiries about reasoning or motivations behind actions and decisions

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

    Conditional statements containing "would"

    np_acts-logits-general · gemini-2.0-flash

    would, would not

    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
    GraphicsUnit
    -0.84
     ternyata
    -0.65
    SuppressMessage
    -0.63
    ViewById
    -0.60
    SequentialGroup
    -0.59
     AssemblyVersion
    -0.57
    TagMode
    -0.57
    AndEndTag
    -0.57
    Према
    -0.57
    zzleHttp
    -0.55
    POSITIVE LOGITS
     would
    2.05
    would
    1.84
     Would
    1.64
    Would
    1.57
     WOULD
    1.48
    wouldn
    1.23
     wouldn
    1.21
     might
    1.14
     zouden
    1.10
     würden
    1.07
    Activations Density 0.338%

    No Known Activations