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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 13031
    Prev
    Next
    INDEX
    Explanations

    corporate and industry names related to technology and legal entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pedals
    -0.40
     saites
    -0.39
     protoimpl
    -0.39
    tidaknya
    -0.39
    AISSEE
    -0.38
    Externé
    -0.38
    ysław
    -0.37
     CallOverrides
    -0.37
     cál
    -0.37
    Personensuche
    -0.36
    POSITIVE LOGITS
     Corporation
    2.56
     corporation
    2.52
     Corp
    2.42
     corp
    2.39
    CORPOR
    2.33
     CORPORATION
    2.31
    Corporation
    2.31
     corporate
    2.30
     CORPOR
    2.28
     corporations
    2.25
    Activations Density 0.523%

    No Known Activations