© 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. 18-GEMMASCOPE-RES-16K
    11. 10864
    Prev
    Next
    INDEX
    Explanations

    elements and attributes related to error handling and message display in code

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

    Code or quotation marks

    np_acts-logits-general · gemini-2.0-flash

    ternary operator or conditional

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.63
    ,
    -0.57
    Personendaten
    -0.54
    via
    -0.47
     buoni
    -0.45
    nocześnie
    -0.45
    Trayectoria
    -0.44
    )(((
    -0.44
    roek
    -0.42
     HomeController
    -0.42
    POSITIVE LOGITS
     than
    0.96
     rather
    0.94
     Rather
    0.89
    rather
    0.87
    <![
    0.85
    Rather
    0.83
     else
    0.83
     sondern
    0.80
     plutôt
    0.79
    IntoConstraints
    0.79
    Activations Density 0.109%

    No Known Activations