© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 13644
    Prev
    Next
    INDEX
    Explanations

    references to people, particularly pronouns and their variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagHelpers
    -0.77
     χ
    -0.70
    rx
    -0.65
     Mot
    -0.65
    Mot
    -0.64
     Bue
    -0.63
     Spire
    -0.63
     Nex
    -0.63
     kurikulum
    -0.61
     Bex
    -0.61
    POSITIVE LOGITS
    Someone
    1.43
    Somebody
    1.34
     Someone
    1.34
    someone
    1.33
     Somebody
    1.30
     someone
    1.26
     Nadie
    1.25
    anyone
    1.24
     SOMEONE
    1.24
    eseorang
    1.20
    Activations Density 0.042%

    No Known Activations