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. 6-GEMMASCOPE-RES-16K
    6. 5240
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to backup systems or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Blanchard
    -0.77
    bourhood
    -0.73
     Erl
    -0.70
     Latimer
    -0.69
     initComponents
    -0.67
     Zay
    -0.65
    getAge
    -0.64
    ngOnInit
    -0.64
     LeBlanc
    -0.63
    tilhe
    -0.63
    POSITIVE LOGITS
     Backing
    1.67
     backing
    1.64
     backed
    1.59
    Backing
    1.55
     backup
    1.32
     Backup
    1.28
     backs
    1.25
    backed
    1.25
    Backup
    1.24
    backing
    1.24
    Activations Density 0.065%

    No Known Activations