© 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. 7-GEMMASCOPE-RES-16K
    11. 7504
    Prev
    Next
    INDEX
    Explanations

    phrases that denote attribution or authorship

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Portale
    -0.69
     crdi
    -0.57
    номер
    -0.55
     مشين
    -0.54
     buhay
    -0.53
    žku
    -0.52
     Objec
    -0.52
    脚注の使い方
    -0.52
    yaf
    -0.51
     boo
    -0.49
    POSITIVE LOGITS
     oleh
    1.49
     by
    1.47
     BY
    1.24
    by
    1.11
     pela
    1.09
     pelos
    1.07
     By
    1.05
     ידי
    1.01
    By
    0.99
     توسط
    0.99
    Activations Density 0.415%

    No Known Activations