© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 5291
    Prev
    Next
    INDEX
    Explanations

    proper nouns and terms related to personal names and locations

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

    followed by specific suffixes

    np_acts-logits-general · gemini-2.0-flash

    specific nouns and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fieldNum
    -0.62
     createState
    -0.59
    Personendaten
    -0.54
    ⟬
    -0.53
    parsedMessage
    -0.52
    AsUp
    -0.51
    <unused51>
    -0.51
    ManagedBean
    -0.51
    <unused43>
    -0.51
    <unused28>
    -0.51
    POSITIVE LOGITS
    CppCodeGen
    0.37
    Tracce
    0.31
    xase
    0.30
     dàng
    0.30
     Wikimedijinoj
    0.29
     maupun
    0.29
     gantung
    0.29
     ""],
    0.28
     regler
    0.28
     anzunehmen
    0.28
    Activations Density 1.566%

    No Known Activations