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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 15989
    Prev
    Next
    INDEX
    Explanations

    elements indicating absence or lack of specific detail

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

    Punctuations and symbols

    np_acts-logits-general · gemini-2.0-flash

    technology data coder

    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
     مشين
    -0.89
     CreateTagHelper
    -0.83
    setVerticalGroup
    -0.83
     '\\;'
    -0.82
    __':
    
    -0.81
    fjspx
    -0.79
     InputDecoration
    -0.78
    SequentialGroup
    -0.78
    IUrlHelper
    -0.76
    LookAnd
    -0.75
    POSITIVE LOGITS
    .
    0.53
     Technology
    0.49
     Sachen
    0.48
     <
    0.48
    coder
    0.46
    0.46
     Technologie
    0.46
    Data
    0.44
    Technology
    0.44
     technologie
    0.43
    Activations Density 0.156%

    No Known Activations