Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 2368
    Prev
    Next
    INDEX
    Explanations

    file paths and directory structures related to the Python environment, particularly in the context of package management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setVerticalGroup
    -0.44
     dr
    -0.44
    SequentialGroup
    -0.43
     “
    -0.42
     anon
    -0.41
    ▼
    -0.40
    พล
    -0.40
    мога
    -0.40
     lotto
    -0.40
     basic
    -0.40
    POSITIVE LOGITS
    InputBorder
    0.76
     ~/
    0.70
    الحياه
    0.67
    onViewCreated
    0.66
     BoxFit
    0.66
    cemment
    0.66
    ActionCreators
    0.65
    IndentedString
    0.63
     nahilalakip
    0.63
     aDecoder
    0.63
    Activations Density 0.142%

    No Known Activations