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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 4114
    Prev
    Next
    INDEX
    Explanations

    variables and function definitions in programming contexts

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

    Code snippets with variables or names

    np_acts-logits-general · gemini-2.0-flash

    assignment of variables

    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
    +#+#
    -0.54
     <>",
    -0.54
    <eos>
    -0.50
    mainAxisSize
    -0.50
     Roskov
    -0.48
    Personendaten
    -0.48
    Itoa
    -0.47
     виправивши
    -0.45
    StructEnd
    -0.44
     rosse
    -0.44
    POSITIVE LOGITS
     disambiguazione
    0.81
    WithIOException
    0.72
    ";}
    0.69
    COUVER
    0.65
     rather
    0.64
     transfieras
    0.64
     Rather
    0.62
    раздо
    0.62
    ówczas
    0.62
    principalTable
    0.60
    Activations Density 0.239%

    No Known Activations