© 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. 22-GEMMASCOPE-RES-16K
    11. 11533
    Prev
    Next
    INDEX
    Explanations

    words related to loss and consequences

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

    Possessive pronouns followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    possessive pronouns + personal nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CodedInputStream
    -0.61
    mmation
    -0.59
     cientí
    -0.53
     bakgrund
    -0.52
    VolleyError
    -0.50
     verschiedener
    -0.50
     ulike
    -0.50
    âtre
    -0.49
    marshaller
    -0.49
    bewerken
    -0.48
    POSITIVE LOGITS
    好不容易
    1.04
     cherished
    0.92
     beloved
    0.90
     valuable
    0.88
     entire
    0.86
     precious
    0.85
     hopes
    0.85
     treasured
    0.84
    innoc
    0.79
    原本
    0.78
    Activations Density 0.552%

    No Known Activations