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. 16-GEMMASCOPE-RES-16K
    6. 14747
    Prev
    Next
    INDEX
    Explanations

    terms related to seeking or searching for something

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

    Sentences containing "seek" or its variations

    np_acts-logits-general · gemini-2.0-flash

    seeking out or achieving

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ftagPool
    -0.85
    
    -0.81
    ViewFeatures
    -0.75
    CopyWith
    -0.73
    mappedBy
    -0.72
     DataTypes
    -0.71
    XmlAccessorType
    -0.69
    XtraEditors
    -0.67
    UserScript
    -0.66
    MigrationBuilder
    -0.65
    POSITIVE LOGITS
     seek
    1.12
     sought
    1.00
     SEEK
    0.99
     seeking
    0.98
     seeks
    0.98
     Seeking
    0.97
     Seek
    0.97
    Seek
    0.85
    Seeking
    0.85
    SEEK
    0.85
    Activations Density 0.076%

    No Known Activations