© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 12800
    Prev
    Next
    INDEX
    Explanations

    terms related to dimensions and measurements, particularly focusing on diameter

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    artament
    -0.51
     ब्रेकडाउन
    -0.51
    GOTREF
    -0.49
     predeceased
    -0.48
    oyant
    -0.47
    tangentMode
    -0.46
    ittarius
    -0.46
    ustimmung
    -0.46
     باك
    -0.46
     touted
    -0.46
    POSITIVE LOGITS
     afterwards
    0.66
    Afterwards
    0.57
     Afterwards
    0.56
     thoroughly
    0.54
    sw
    0.54
     thorough
    0.52
     afterward
    0.48
     diagonal
    0.47
     "..\..\..\
    0.45
     Official
    0.44
    Activations Density 0.121%

    No Known Activations