Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 6964
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to exclusivity

    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
    *}$
    -0.84
    yargs
    -0.71
    MigrationBuilder
    -0.69
    🏼
    -0.69
    ProcessEvent
    -0.69
    NTS
    -0.69
     Dord
    -0.67
     ControllerBase
    -0.66
    🏽
    -0.66
    ChromeDriver
    -0.65
    POSITIVE LOGITS
     Exclu
    1.36
     Exclusive
    1.35
     exclusive
    1.35
    Exclusive
    1.28
    EXCLUSIVE
    1.26
     EXCLUSIVE
    1.24
    Exclu
    1.23
     exclu
    1.20
     exclusives
    1.20
    exclusive
    1.14
    Activations Density 0.090%

    No Known Activations