© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 10294
    Prev
    Next
    INDEX
    Explanations

    instances of the pronoun "it," indicating a focus on references to subjects or objects previously mentioned in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monfieur
    -1.65
     doubtnut
    -1.52
     Majefty
    -1.50
     Anſ
    -1.48
     Houſe
    -1.46
     pleaſure
    -1.45
     ―――――
    -1.44
     raiſ
    -1.41
     Reſ
    -1.40
     Efq
    -1.40
    POSITIVE LOGITS
     it
    3.93
     It
    3.06
    It
    2.83
    it
    2.26
    它
    2.15
     its
    1.80
     它
    1.79
     IT
    1.75
     nó
    1.68
    มัน
    1.60
    Activations Density 0.310%

    No Known Activations