© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 5212
    Prev
    Next
    INDEX
    Explanations

    references to programming concepts and structures such as tables, queries, and object properties within code

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

    programming code and technical syntax elements, particularly related to software development and code structure.

    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
     defaultstate
    -0.44
    __;
    -0.37
    NOPQRST
    -0.36
     aanv
    -0.35
    execSQL
    -0.34
     calciatore
    -0.34
     
    -0.32
    ̅
    -0.32
    sti
    -0.32
    MP
    -0.32
    POSITIVE LOGITS
     betweenstory
    0.75
     desmotivaciones
    0.65
    رشف
    0.60
    المكان
    0.57
    väg
    0.56
    fromnode
    0.55
    vorschaubild
    0.55
     ConstraintSet
    0.55
    ContainerState
    0.53
     Autorizaciones
    0.53
    Activations Density 1.600%

    No Known Activations