Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 323
    Prev
    Next
    INDEX
    Explanations

    conjunctions and phrases indicating reciprocity or mutual relationships

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

    preceding or following "vice versa"

    np_acts-logits-general · gemini-2.0-flash

    vice versa

    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
    ын
    -0.52
    Πηγές
    -0.51
    atschappij
    -0.48
    üben
    -0.47
     >=",
    -0.47
    gradable
    -0.45
    ImageIO
    -0.44
    articulo
    -0.44
    wolle
    -0.44
     newOwner
    -0.43
    POSITIVE LOGITS
     vice
    3.29
     viceversa
    2.39
     Vice
    2.28
     umgekehrt
    2.26
    vice
    2.24
    Vice
    2.18
     vise
    2.01
     conversely
    1.97
     VICE
    1.84
     Conversely
    1.79
    Activations Density 0.209%

    No Known Activations