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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 2916
    Prev
    Next
    INDEX
    Explanations

    the use of terms indicating prior introduction or prior results in discussions or theories

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

    already been

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     незавершена
    -0.69
     وتسجيلات
    -0.68
    ghijkl
    -0.63
    DispatchToProps
    -0.63
     BaseActivity
    -0.61
     EconPapers
    -0.59
     Offisielt
    -0.59
    RegressionTest
    -0.58
    StructEnd
    -0.58
     onOptions
    -0.58
    POSITIVE LOGITS
    EntityFramework
    0.83
    <?
    0.42
     DbContext
    0.39
    IntoConstraints
    0.36
    SpringBootTest
    0.35
     knex
    0.31
    ächlich
    0.30
     BrowserModule
    0.29
     projet
    0.29
    assertj
    0.29
    Activations Density 0.000%

    No Known Activations