© 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. 11855
    Prev
    Next
    INDEX
    Explanations

    specific phrases and terms used in instructions or guidelines

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

    followed by prepositions or articles

    np_acts-logits-general · gemini-2.0-flash

    verbs indicating action

    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
     semn
    -0.34
     picioare
    -0.30
     păr
    -0.30
     userRepository
    -0.30
     înal
    -0.29
     nevoie
    -0.29
     iNdEx
    -0.29
     exemplaires
    -0.29
     opět
    -0.28
     față
    -0.28
    POSITIVE LOGITS
    Personensuche
    0.97
    OGND
    0.93
    Autoritní
    0.68
    antMatchers
    0.65
    Datuak
    0.65
     HttpNotFound
    0.63
    principalTable
    0.63
     Biôgrafia
    0.62
    
    0.61
    expandindo
    0.59
    Activations Density 13.817%

    No Known Activations