© 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-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 7477
    Prev
    Next
    INDEX
    Explanations

    concepts related to mathematical models and physical properties of objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    日閲覧
    -0.76
    帖最后由
    -0.73
    Datuak
    -0.67
    MigrationBuilder
    -0.67
     архивлан
    -0.66
    InstrumentedTest
    -0.66
    ChildScrollView
    -0.64
    fastjson
    -0.63
    RegistryLite
    -0.63
    igshid
    -0.63
    POSITIVE LOGITS
    برى
    0.50
    IntoConstraints
    0.44
    migrationBuilder
    0.43
     rond
    0.39
     pysty
    0.39
     embra
    0.39
     transfieras
    0.39
     weil
    0.38
     примерно
    0.38
    加坡
    0.38
    Activations Density 1.123%

    No Known Activations