© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 4710
    Prev
    Next
    INDEX
    Explanations

    phrases related to conclusions and summaries of events or series

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.58
    nestjs
    -0.57
    SpringRunner
    -0.56
    ANGE
    -0.55
    ➋
    -0.54
     useDispatch
    -0.54
     GetEnumerator
    -0.53
    UALA
    -0.53
    CGRectMake
    -0.53
    ⎨
    -0.52
    POSITIVE LOGITS
     final
    2.06
     finale
    1.98
     concluding
    1.93
    final
    1.75
     closing
    1.75
    Final
    1.64
     conclusion
    1.63
     Concluding
    1.60
     Final
    1.57
     finales
    1.57
    Activations Density 0.467%

    No Known Activations