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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 18-GEMMASCOPE-RES-16K
    6. 10103
    Prev
    Next
    INDEX
    Explanations

    references to hard work and determination in achieving success

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.84
    BeginContext
    -0.72
     CreateTagHelper
    -0.63
     createStore
    -0.62
    SerializedName
    -0.61
    PerformLayout
    -0.61
    ArrowToggle
    -0.59
     createState
    -0.56
    ViewImports
    -0.55
    RegressionTest
    -0.55
    POSITIVE LOGITS
     hardworking
    1.36
     work
    1.20
     industrious
    1.17
     hard
    1.14
     Work
    1.07
     WORK
    1.07
    work
    1.07
    Work
    1.07
     diligence
    1.06
     effort
    1.04
    Activations Density 0.174%

    No Known Activations