© 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. 33-GEMMASCOPE-RES-16K
    11. 2452
    Prev
    Next
    INDEX
    Explanations

    narrative elements and themes related to quests, challenges, and stories in a fantastical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     similar
    -0.44
     esetén
    -0.42
     like
    -0.35
     including
    -0.28
    similar
    -0.28
     Similar
    -0.25
    Similar
    -0.25
     similares
    -0.23
     como
    -0.23
     different
    -0.23
    POSITIVE LOGITS
     itself
    1.03
    itself
    0.98
     témoig
    0.98
     queſta
    0.96
     tartalo
    0.96
     Dieſe
    0.93
    <pad>
    0.93
    <unused74>
    0.92
    <unused43>
    0.92
    <unused41>
    0.92
    Activations Density 2.595%

    No Known Activations