© 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. 20-GEMMASCOPE-RES-16K
    11. 7273
    Prev
    Next
    INDEX
    Explanations

    Java import statements related to web services and annotations

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

    Java-related imports or packages

    np_acts-logits-general · gemini-2.0-flash

    Java imports

    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
    forChild
    -0.71
    +#+#
    -0.67
    antaranya
    -0.67
     unknownFields
    -0.64
    OutputType
    -0.62
    SourceChecksum
    -0.60
    RegressionTest
    -0.60
    MockBean
    -0.60
    providedIn
    -0.60
    copyWith
    -0.59
    POSITIVE LOGITS
    OrNil
    0.60
    validation
    0.58
    annotation
    0.58
    sound
    0.58
     seriously
    0.54
     Oppen
    0.53
    swing
    0.52
     Obec
    0.52
     WN
    0.52
    undred
    0.51
    Activations Density 0.027%

    No Known Activations