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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 23-GEMMASCOPE-RES-16K
    6. 10421
    Prev
    Next
    INDEX
    Explanations

    mentions of the pronoun "I" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BorderRadius
    -0.82
    ChildScrollView
    -0.76
     '\\;'
    -0.76
    aarrggbb
    -0.76
    OGND
    -0.72
    SharedDtor
    -0.72
     DriverManager
    -0.72
    bootstrapcdn
    -0.71
     utafitiHapana
    -0.70
     nameof
    -0.68
    POSITIVE LOGITS
     tried
    0.76
     assume
    0.65
     tested
    0.64
     searched
    0.64
     notice
    0.62
     noticed
    0.61
     checked
    0.60
     experimented
    0.57
     presume
    0.57
     wondered
    0.57
    Activations Density 0.318%

    No Known Activations