© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 14043
    Prev
    Next
    INDEX
    Explanations

    geographical locations and their related context

    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
    IsContent
    -0.67
     surla
    -0.65
     createSlice
    -0.60
     doInBackground
    -0.60
     saites
    -0.59
     BoxDecoration
    -0.58
     aDecoder
    -0.57
    principalColumn
    -0.57
     TestBed
    -0.56
    OCCURRED
    -0.56
    POSITIVE LOGITS
     Galway
    0.44
     Geelong
    0.41
     архивлан
    0.36
    Bain
    0.33
     Purdue
    0.32
     galle
    0.32
     Ekiti
    0.31
     Compos
    0.30
    zmir
    0.29
     Bain
    0.29
    Activations Density 0.237%

    No Known Activations