© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 7519
    Prev
    Next
    INDEX
    Explanations

    references to treatment methods and their effectiveness in a medical context

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

    Commas and semicolons

    np_acts-logits-general · gemini-2.0-flash

    list item separators and concluding words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WriteTagHelper
    -0.58
    parsedMessage
    -0.56
    ├──
    -0.56
     ſei
    -0.55
    verwijspagina
    -0.54
     CallOverrides
    -0.54
    endphp
    -0.54
    ьаж
    -0.53
    Наводи
    -0.53
    Istwa
    -0.53
    POSITIVE LOGITS
     lastly
    0.63
    Lastly
    0.60
    └──
    0.59
     Lastly
    0.59
     finally
    0.58
     Finally
    0.57
    finally
    0.57
    Finally
    0.55
    Finalmente
    0.48
     enfin
    0.47
    Activations Density 0.360%

    No Known Activations