© 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. 11-GEMMASCOPE-RES-16K
    11. 10359
    Prev
    Next
    INDEX
    Explanations

    code that includes string manipulation functions, specifically those for splitting and joining strings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IGENCE
    -0.52
    vode
    -0.49
     افز
    -0.46
     HasFactory
    -0.42
    erne
    -0.42
     Photocase
    -0.41
     presence
    -0.40
    CGContext
    -0.40
     utafitiHapana
    -0.40
    ьажоргаш
    -0.39
    POSITIVE LOGITS
    split
    1.72
     split
    1.57
    Split
    1.48
     Split
    1.48
    SPLIT
    1.23
     splits
    1.17
     splitting
    1.15
    splitting
    1.09
    splits
    1.02
    plit
    0.97
    Activations Density 0.326%

    No Known Activations