© 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. 3-GEMMASCOPE-RES-16K
    11. 619
    Prev
    Next
    INDEX
    Explanations

    phrases that signify a role or participation within a group or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ponses
    -0.65
     Arquivado
    -0.63
    逆に
    -0.60
     individuale
    -0.59
     PLW
    -0.59
     Islamist
    -0.58
     Wilfred
    -0.57
    kháu
    -0.57
     recipro
    -0.55
     बजाय
    -0.55
    POSITIVE LOGITS
     part
    1.69
     parts
    1.23
     parte
    1.19
    part
    1.08
     часть
    0.95
     portion
    0.95
    parts
    0.88
     bagian
    0.87
     Bestandteil
    0.83
     PART
    0.83
    Activations Density 0.101%

    No Known Activations