© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 8106
    Prev
    Next
    INDEX
    Explanations

    references to data management and error handling in software applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 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
     становника
    -0.99
     فريبيس
    -0.97
    ]")]
    -0.96
     kasarigan
    -0.95
     EconPapers
    -0.93
    uxxxx
    -0.93
     MainAxisSize
    -0.92
    PreferredItem
    -0.90
     utafitiHapana
    -0.90
     مشين
    -0.90
    POSITIVE LOGITS
    <bos>
    0.53
    <eos>
    0.49
    ↵↵
    0.47
    </em>
    0.41
     of
    0.38
     He
    0.38
    :
    0.38
    ,
    0.38
     on
    0.38
     Hall
    0.37
    Activations Density 0.179%

    No Known Activations