© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105885
    Prev
    Next
    INDEX
    Explanations

    code-related elements, particularly focusing on class structures and function definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text segment that introduces code snippets, often using "in" followed by file type specification (like ".h") or phrases like "use as follows", "the same", "my", "then have this", "in my" to transition between code explanation and implementation examples.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſch
    -0.84
     للاسماء
    -0.82
     queſta
    -0.81
     houſe
    -0.80
     незавершена
    -0.78
     Efq
    -0.78
    StructEnd
    -0.77
     мәкал
    -0.77
    MemoryWarning
    -0.77
     ſei
    -0.76
    POSITIVE LOGITS
     pasamos
    0.34
    brigens
    0.33
    And
    0.32
    SOL
    0.32
     Check
    0.32
    IF
    0.31
     related
    0.31
    引
    0.31
    ::
    0.30
     meny
    0.30
    Activations Density 0.224%

    No Known Activations