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. 5-GEMMASCOPE-RES-16K
    6. 16067
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific methods and procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CloseOperation
    -0.81
    aarrggbb
    -0.81
    脚注の使い方
    -0.79
    SharedDtor
    -0.79
    mybatisplus
    -0.78
     BoxFit
    -0.77
    AddTagHelper
    -0.77
     nakalista
    -0.77
     Theſe
    -0.76
     pinulongan
    -0.74
    POSITIVE LOGITS
     INVENTION
    0.59
    <bos>
    0.49
     embodiments
    0.44
     is
    0.44
     embodiment
    0.43
     []).
    0.42
    omány
    0.42
    льф
    0.42
     متحده
    0.42
    _______
    0.40
    Activations Density 1.087%

    No Known Activations