© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13199
    Prev
    Next
    INDEX
    Explanations

    discussions surrounding accountability and individual actions in various contexts

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

    Followed by "to" or a verb

    np_acts-logits-general · gemini-2.0-flash

    trying to get

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    fjspx
    -0.57
    tagHelper
    -0.43
    queryInterface
    -0.43
     NgModule
    -0.42
    setupUi
    -0.40
     graders
    -0.39
    CodeAttribute
    -0.39
    FieldBuilder
    -0.39
     protoimpl
    -0.38
    MigrationBuilder
    -0.37
    POSITIVE LOGITS
     kasarigan
    0.66
    CloseOperation
    0.45
    [@
    0.40
     informée
    0.40
     defen
    0.40
    prote
    0.40
     titolata
    0.40
    sekten
    0.40
     deflected
    0.39
     secado
    0.38
    Activations Density 0.538%

    No Known Activations