© 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. 20-GEMMASCOPE-RES-16K
    6. 8446
    Prev
    Next
    INDEX
    Explanations

    references to statistical models and methods

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

    References and citations

    np_acts-logits-general · gemini-2.0-flash

    span style, ref citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/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.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SaveChangesAsync
    -0.83
     المعيارى
    -0.81
    tagext
    -0.80
     }}$}
    -0.76
     MainAxisSize
    -0.74
    CppCodeGen
    -0.74
    })$}
    -0.73
    CompleteListener
    -0.73
    msgSender
    -0.72
    endphp
    -0.72
    POSITIVE LOGITS
    ##
    0.59
    mso
    0.57
    <eos>
    0.52
     Regener
    0.52
    
    
    0.52
    _
    0.51
    λει
    0.51
    End
    0.48
    wn
    0.48
     Godhead
    0.48
    Activations Density 2.775%

    No Known Activations