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. 7-GEMMASCOPE-RES-16K
    6. 9316
    Prev
    Next
    INDEX
    Explanations

    references to the word "it" 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
     cauſe
    -0.97
     whoſe
    -0.89
     pleaſure
    -0.89
     Eſ
    -0.86
     reaſon
    -0.86
     faſt
    -0.85
     caufe
    -0.85
     ſtre
    -0.83
     deſt
    -0.82
    DAQ
    -0.81
    POSITIVE LOGITS
     it
    1.04
     виправивши
    0.74
     him
    0.73
     It
    0.73
    éndolo
    0.72
     them
    0.70
     AssemblyCulture
    0.70
     here
    0.67
    doit
    0.67
     initComponents
    0.67
    Activations Density 0.183%

    No Known Activations