© 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. 12807
    Prev
    Next
    INDEX
    Explanations

    phrases that introduce relative clauses

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

    "that" preceding a verb

    np_acts-logits-general · gemini-2.0-flash

    relative pronouns followed by verbs

    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
     coopération
    -0.38
    !
    -0.32
    ,
    -0.32
    ių
    -0.30
     pří
    -0.29
     soldadura
    -0.28
    ess
    -0.28
     cours
    -0.28
    ?
    -0.28
    Bonus
    -0.27
    POSITIVE LOGITS
     CreateTagHelper
    0.73
    出版年
    0.69
     ddelwed
    0.69
     мәкал
    0.69
     ſei
    0.69
    fjspx
    0.69
     dieſes
    0.68
     تضيفلها
    0.67
    <unused14>
    0.67
    <unused23>
    0.67
    Activations Density 0.448%

    No Known Activations