© 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. 2-GEMMASCOPE-RES-16K
    11. 1372
    Prev
    Next
    INDEX
    Explanations

    the word "those" and related terms indicating reference or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éril
    -0.66
     Micah
    -0.60
    Micah
    -0.59
    pragma
    -0.58
    Jum
    -0.55
     которому
    -0.55
     което
    -0.55
     ruine
    -0.53
     pierre
    -0.53
    firstChild
    -0.53
    POSITIVE LOGITS
     those
    2.94
    those
    2.67
    Those
    2.63
     Those
    2.51
     THOSE
    2.33
     these
    1.82
     thoſe
    1.66
    那些
    1.66
     aquellos
    1.60
     aqueles
    1.59
    Activations Density 0.124%

    No Known Activations