© 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. 4263
    Prev
    Next
    INDEX
    Explanations

    specific programming structures and elements related to variable declarations and assignments

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

    PHP and variable names

    np_acts-logits-general · gemini-2.0-flash

    variable / variables

    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
     ujednoznacz
    -0.51
    ctez
    -0.48
    CodedInputStream
    -0.47
    ondon
    -0.46
     dream
    -0.45
     colspan
    -0.43
     Ceinture
    -0.43
    mosa
    -0.42
     ویکی‌پدیا
    -0.42
     Boe
    -0.42
    POSITIVE LOGITS
     variable
    3.09
     Variable
    2.89
     var
    2.81
    variable
    2.81
    Var
    2.80
    Variable
    2.74
     Var
    2.73
     variables
    2.63
     VARIABLE
    2.58
     vari
    2.55
    Activations Density 0.440%

    No Known Activations