© 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. 4-GEMMASCOPE-RES-16K
    11. 928
    Prev
    Next
    INDEX
    Explanations

    terms related to gold, indicating references to precious metals and awards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /*
    -0.79
    rég
    -0.71
     PTI
    -0.67
     Bernal
    -0.66
    ษัท
    -0.65
     Dept
    -0.63
     Cranston
    -0.63
    遽
    -0.60
     onPostExecute
    -0.60
    theilung
    -0.59
    POSITIVE LOGITS
     Gold
    2.70
     gold
    2.60
    Gold
    2.56
    gold
    2.41
     GOLD
    2.39
    GOLD
    2.15
    ゴールド
    1.49
     gouden
    1.48
     golden
    1.45
    golden
    1.44
    Activations Density 0.033%

    No Known Activations