© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 7990
    Prev
    Next
    INDEX
    Explanations

    lines of code or method definitions in programming-related text

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

    data retrieval

    np_acts-logits-general · gemini-2.0-flash

    get and retrieve

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     дописавши
    -0.60
     addUser
    -0.59
     nahilalakip
    -0.56
     newItem
    -0.55
    SharedDtor
    -0.54
     <=",
    -0.53
    expandindo
    -0.53
     beginnetje
    -0.53
    addEdge
    -0.51
    addNode
    -0.51
    POSITIVE LOGITS
     retrieve
    1.33
     retrieving
    1.28
     Get
    1.23
     Retrieve
    1.22
     retrieval
    1.22
     retrieves
    1.20
     get
    1.19
    Get
    1.17
     GET
    1.14
    获取
    1.13
    Activations Density 0.586%

    No Known Activations