© 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. 7044
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to variable assignments and object instantiation

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

    Equals signs followed by "new"

    np_acts-logits-general · gemini-2.0-flash

    object instantiation with `new`

    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
    antMatchers
    -0.63
     paramInt
    -0.56
     plat
    -0.51
    PreferredItem
    -0.46
    obic
    -0.45
    migrationBuilder
    -0.45
    usz
    -0.44
     stano
    -0.42
     BIG
    -0.42
     gam
    -0.42
    POSITIVE LOGITS
     itſelf
    0.77
     mukana
    0.77
    ſelf
    0.76
    RectangleBorder
    0.73
     doigts
    0.72
     Jefus
    0.72
    })*/
    0.72
     démocr
    0.71
    });
    0.71
     preſent
    0.69
    Activations Density 0.103%

    No Known Activations