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. 6166
    Prev
    Next
    INDEX
    Explanations

    terms related to entry and access points in various contexts

    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
     CreateTagHelper
    -0.92
    PerformLayout
    -0.82
    IUrlHelper
    -0.76
     calendriers
    -0.74
     Wicidata
    -0.73
     AssemblyCulture
    -0.67
    NewUrlParser
    -0.66
    ChildScrollView
    -0.66
    ]")]
    -0.64
     surla
    -0.62
    POSITIVE LOGITS
     entry
    1.27
     entrance
    1.23
     Entry
    1.16
     entrada
    1.12
     entrances
    1.07
     ingresso
    1.05
     Entrance
    1.05
    entrance
    1.02
    Entrance
    1.01
    Entry
    0.98
    Activations Density 0.470%

    No Known Activations