© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 962
    Prev
    Next
    INDEX
    Explanations

    programming constructs or keywords related to data structure management

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

    code-related keywords and programming syntax elements.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     محفوظة
    -0.41
     informée
    -0.40
    RectangleBorder
    -0.40
    inflater
    -0.38
     animación
    -0.38
     BoxDecoration
    -0.38
     незавершена
    -0.37
     useAppContext
    -0.36
     referenties
    -0.36
     externi
    -0.34
    POSITIVE LOGITS
     تانيه
    0.58
    Хьажоргаш
    0.58
     <<<<<<<<<<<<<<
    0.52
    хьтан
    0.49
    WaitGroup
    0.49
     Spal
    0.47
    IndentedString
    0.47
     pleaſure
    0.45
    튿
    0.45
     KAT
    0.44
    Activations Density 1.483%

    No Known Activations