© 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. 12-GEMMASCOPE-RES-16K
    11. 12805
    Prev
    Next
    INDEX
    Explanations

    phrases related to division and separation within data or structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الحره
    -0.46
    netinet
    -0.44
    SuccessListener
    -0.43
    הערות
    -0.42
    glDisable
    -0.41
     Applied
    -0.41
    EFIAPI
    -0.41
     typelib
    -0.40
    ostoma
    -0.39
    applied
    -0.38
    POSITIVE LOGITS
     split
    1.35
     splits
    1.24
     splitting
    1.24
     Split
    1.16
     divide
    1.15
     divides
    1.11
    split
    1.09
     divided
    1.09
    Split
    1.09
     dividir
    1.05
    Activations Density 0.831%

    No Known Activations