© 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. 16-GEMMASCOPE-RES-16K
    6. 7879
    Prev
    Next
    INDEX
    Explanations

    instructional verbs and phrases related to processes or steps

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    sequence or conclusion

    np_acts-logits-general · gemini-2.0-flash

    signals transition or next step

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estekak
    -0.97
     kasarigan
    -0.91
     purpoſe
    -0.85
     SwitchCompat
    -0.83
     itſelf
    -0.83
    ſelves
    -0.82
    XmlAccessorType
    -0.82
     themſelves
    -0.81
     himſelf
    -0.80
     myſelf
    -0.79
    POSITIVE LOGITS
    いよいよ
    0.80
     Finally
    0.77
     finally
    0.75
    Finally
    0.74
     Lastly
    0.66
    Lastly
    0.66
    Next
    0.65
     next
    0.65
    あとは
    0.65
     proceed
    0.63
    Activations Density 0.375%

    No Known Activations