© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3689
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to software assemblies and their attributes

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

    before "following" and "winning"

    np_acts-logits-general · gemini-2.0-flash

    following descriptors

    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
    machus
    -0.51
    Sucesor
    -0.48
     seleção
    -0.48
    AutoScale
    -0.48
    وعة
    -0.48
    ParseTree
    -0.47
     degeneracy
    -0.47
    cembre
    -0.46
     Ratios
    -0.45
    CWE
    -0.44
    POSITIVE LOGITS
    InteropServices
    1.39
    }")]
    0.61
    plevel
    0.59
    hals
    0.59
     Luf
    0.58
    bibfield
    0.58
    ImageContext
    0.56
    CompilerServices
    0.56
    >\<^
    0.55
    )}</
    0.55
    Activations Density 0.024%

    No Known Activations