© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 12015
    Prev
    Next
    INDEX
    Explanations

    numerical values and punctuation in contextual references

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

    Sentences ending with a period

    np_acts-logits-general · gemini-2.0-flash

    finally and lastly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الرياضيه
    -0.57
    Демографія
    -0.50
    要不
    -0.45
     CanadaChoose
    -0.43
    gnus
    -0.43
    يميديا
    -0.43
    請繼續往下閱讀
    -0.43
    JvmStatic
    -0.41
     مشين
    -0.40
    penn
    -0.40
    POSITIVE LOGITS
     Finally
    0.70
     finally
    0.66
     lastly
    0.65
    Finally
    0.63
     Lastly
    0.63
     enfin
    0.59
     both
    0.59
    Lastly
    0.58
     Both
    0.55
     infine
    0.53
    Activations Density 0.853%

    No Known Activations