© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 6084
    Prev
    Next
    INDEX
    Explanations

    HTTP status codes and error messages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /**
    -0.77
     Paglinawan
    -0.75
    таратура
    -0.74
     Meksiku
    -0.74
    JspWriter
    -0.72
    Джерела
    -0.69
    elemField
    -0.67
    )]);
    -0.67
    حياته
    -0.66
    )));
    
    -0.66
    POSITIVE LOGITS
     كومونز
    0.77
    GHIJKLM
    0.59
    CppCodeGen
    0.58
    tidae
    0.58
    IActionResult
    0.52
    gdala
    0.51
    TagHelpers
    0.51
    ához
    0.49
    petual
    0.49
    RAINT
    0.49
    Activations Density 0.069%

    No Known Activations