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. 14-GEMMASCOPE-RES-16K
    6. 10650
    Prev
    Next
    INDEX
    Explanations

    variations of the word "thing" and its contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    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
    -1.11
    ChildScrollView
    -1.09
     myſelf
    -1.08
     ſever
    -1.08
     fevere
    -1.07
     juſ
    -1.07
     uſe
    -1.01
     poffible
    -0.98
     ſtate
    -0.97
     juſt
    -0.97
    POSITIVE LOGITS
     things
    1.70
     thing
    1.64
     Thing
    1.54
     Things
    1.50
     THINGS
    1.50
    Things
    1.50
     THING
    1.49
    Thing
    1.34
    things
    1.32
    THING
    1.19
    Activations Density 0.111%

    No Known Activations