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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 8593
    Prev
    Next
    INDEX
    Explanations

    abbreviations and acronyms

    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
    ILayout
    -0.67
     Roskov
    -0.66
     cref
    -0.61
    GEBURTSDATUM
    -0.61
     ***!
    -0.60
     propOrder
    -0.58
    BASELINE
    -0.57
    Referanser
    -0.56
    PerformLayout
    -0.56
    FontOfSize
    -0.56
    POSITIVE LOGITS
    componentWill
    0.70
    ſelves
    0.66
     pleaſure
    0.66
     tfsi
    0.64
     partea
    0.64
     '{{
    0.63
     greateſt
    0.61
     '<?
    0.60
     Diſ
    0.59
    <bos>
    0.59
    Activations Density 0.818%

    No Known Activations