© 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. 7-GEMMASCOPE-RES-16K
    11. 4755
    Prev
    Next
    INDEX
    Explanations

    references to "things" and "stuff" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pleaſure
    -1.10
     myſelf
    -1.09
     fevere
    -1.05
     uſe
    -1.05
     juſ
    -1.05
     ſtre
    -1.02
     ſever
    -1.02
     juſt
    -1.01
     uſed
    -1.01
     ſet
    -0.98
    POSITIVE LOGITS
     thing
    2.07
     things
    1.97
     Thing
    1.88
     THING
    1.82
    Things
    1.75
     Things
    1.74
     THINGS
    1.74
    Thing
    1.67
    things
    1.56
    THING
    1.50
    Activations Density 0.054%

    No Known Activations