© 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-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 8277
    Prev
    Next
    INDEX
    Explanations

    technical terms related to electronic signal processing and logical circuitry

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

    following "the", "of", "and", "with" and "for"

    np_acts-logits-general · gemini-2.0-flash

    words following common prepositions and articles

    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
     seems
    -0.34
     what
    -0.32
     seem
    -0.30
     jorden
    -0.29
     Naciones
    -0.29
     often
    -0.28
     endroits
    -0.28
     siècles
    -0.28
     vôtre
    -0.27
     such
    -0.27
    POSITIVE LOGITS
    parsedMessage
    0.90
     autorytatywna
    0.87
     témoig
    0.85
    verifyException
    0.81
     パンチラ
    0.80
    ſicht
    0.79
     ویکی‌پدی
    0.79
     ब्रेकडाउन
    0.78
    <unused41>
    0.77
    AccessorTable
    0.77
    Activations Density 4.278%

    No Known Activations