© 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. 1131
    Prev
    Next
    INDEX
    Explanations

    terms related to conditional situations and potential outcomes

    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
    HomeAsUpEnabled
    -0.58
    URLException
    -0.56
    ControllerAdvice
    -0.55
    Parcelize
    -0.50
     protoimpl
    -0.49
    BASELINE
    -0.49
    getUid
    -0.48
     convertView
    -0.48
    felf
    -0.48
    存于互联网档案馆
    -0.48
    POSITIVE LOGITS
     without
    3.98
    without
    3.56
     Without
    3.43
    Without
    3.36
     WITHOUT
    3.03
     zonder
    3.00
     ohne
    2.88
    WITHOUT
    2.84
     senza
    2.84
     tanpa
    2.83
    Activations Density 1.529%

    No Known Activations