© 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. 16-GEMMASCOPE-RES-16K
    11. 5372
    Prev
    Next
    INDEX
    Explanations

    programming-related function and method calls

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

    Code snippets and programming terms

    np_acts-logits-general · gemini-2.0-flash

    codes and technical English terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Paglinawan
    -0.73
    sidemargin
    -0.66
    LookAnd
    -0.65
    onAttach
    -0.55
    webElementXpaths
    -0.55
    MarshalTo
    -0.55
     end
    -0.54
    BUMP
    -0.53
     No
    -0.52
     {}",
    -0.51
    POSITIVE LOGITS
    seamnă
    0.74
     houſe
    0.71
     Jefus
    0.66
    ſelf
    0.64
     Majefty
    0.64
     NSCoder
    0.63
     ſtate
    0.63
     pleaſure
    0.63
     Efq
    0.61
     Eſ
    0.60
    Activations Density 0.086%

    No Known Activations