© 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. 20-GEMMASCOPE-RES-16K
    11. 16281
    Prev
    Next
    INDEX
    Explanations

    text related to roles and responsibilities in a work or engineering context

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

    The neuron activates strongly at the beginning of documents or paragraphs, particularly after line breaks and at the start of new sections of text.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.72
     חיצוניים
    -0.69
     surla
    -0.67
    \{\\
    -0.67
    ########.
    -0.65
    GOTREF
    -0.64
     ujednoznacz
    -0.61
    ⓧ
    -0.60
    İstinadlar
    -0.59
     հղումներ
    -0.59
    POSITIVE LOGITS
     your
    0.38
    Your
    0.35
     Your
    0.35
    PACS
    0.32
    your
    0.32
     whiteColor
    0.32
    !
    0.31
     servici
    0.30
     disesuaikan
    0.30
     mView
    0.29
    Activations Density 0.018%

    No Known Activations