© 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. 3653
    Prev
    Next
    INDEX
    Explanations

    code elements related to memory management and pointer usage

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

    programming-related terminology about pointers, memory management, and smart pointer types.

    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
    sizeCache
    -0.51
    tvguidetime
    -0.50
    حياته
    -0.47
    AddTagHelper
    -0.46
     nonUne
    -0.45
    Rüyada
    -0.44
    /*
    -0.44
    xase
    -0.44
     OFDb
    -0.44
    сылкі
    -0.43
    POSITIVE LOGITS
     ElementRef
    0.53
     JAXBElement
    0.50
     Numerade
    0.49
    EditPart
    0.48
     useRef
    0.47
    Wrapper
    0.45
    tableFuture
    0.45
    JScrollPane
    0.45
    InputTagHelper
    0.44
    NSNumber
    0.43
    Activations Density 0.269%

    No Known Activations