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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 6890
    Prev
    Next
    INDEX
    Explanations

    occurrences of the abbreviation "ib" and its variations, indicating its focus on information related to specific protocols, methodologies, or data points in research or academic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Schloss
    -0.75
    oara
    -0.73
     Winfield
    -0.72
     Penh
    -0.70
    Trimethyl
    -0.70
     Woody
    -0.70
    Woody
    -0.69
    تقاوى
    -0.69
     Reiche
    -0.67
     FOG
    -0.67
    POSITIVE LOGITS
    ib
    2.58
    IB
    2.01
     IB
    1.81
     ib
    1.71
    Ib
    1.28
     Ib
    1.26
    ibs
    1.14
    iba
    1.05
     Wib
    0.93
    ibi
    0.90
    Activations Density 0.194%

    No Known Activations