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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 2025
    Prev
    Next
    INDEX
    Explanations

    code segments and structures related to programming syntax, particularly focusing on control structures and code blocks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __":
    -0.92
    __":
    -0.90
    __':
    -0.88
    SequentialGroup
    -0.86
     sumpay
    -0.84
    __':
    -0.84
    AndEndTag
    -0.78
    setVerticalGroup
    -0.72
     BoxFit
    -0.72
     dAtA
    -0.72
    POSITIVE LOGITS
     preſent
    0.49
     houſe
    0.48
     Houſe
    0.46
     themſelves
    0.45
     Majefty
    0.43
     Svensk
    0.42
     ſame
    0.42
     þat
    0.42
     Schengen
    0.41
    culada
    0.40
    Activations Density 0.416%

    No Known Activations