© 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. 21-GEMMASCOPE-RES-16K
    11. 8268
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to introductions and social interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.76
     الرياضيه
    -0.76
    \{\\
    -0.72
     EconPapers
    -0.71
     nakalista
    -0.69
     MainAxisSize
    -0.62
    IZABETH
    -0.61
    ποτε
    -0.60
    ](#
    -0.60
    selves
    -0.59
    POSITIVE LOGITS
     peoples
    1.31
     someone
    1.10
    别人的
    1.04
     somebody
    1.04
     everyone
    1.04
    对方的
    1.02
     THEIR
    1.02
     their
    1.01
     everybody
    0.99
    大家的
    0.98
    Activations Density 0.843%

    No Known Activations