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. 4044
    Prev
    Next
    INDEX
    Explanations

    terms related to software components and configurations

    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
    xfb
    -0.50
    PerformLayout
    -0.49
    GetMapping
    -0.48
    IP
    -0.45
    ip
    -0.44
    さんです
    -0.43
    celli
    -0.42
    öfe
    -0.42
    SerializeField
    -0.42
    bra
    -0.42
    POSITIVE LOGITS
    ComponentModel
    1.74
    +:+
    1.25
     sklearn
    1.10
    Clik
    1.00
    NgModule
    0.90
    TabIndex
    0.90
    PMailer
    0.88
    Бахар
    0.85
    BagConstraints
    0.85
     ComVisible
    0.83
    Activations Density 0.012%

    No Known Activations