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. 16263
    Prev
    Next
    INDEX
    Explanations

    references to navigation systems and related concepts

    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
    #+#
    -0.99
    +#+
    -0.77
    ValueStyle
    -0.75
     defaultstate
    -0.72
     ModelExpression
    -0.70
    openzeppelin
    -0.68
    awtextra
    -0.65
    CppCodeGen
    -0.65
    TemporalType
    -0.65
    BeginContext
    -0.64
    POSITIVE LOGITS
     navigation
    1.39
    navigation
    1.35
     Navigation
    1.34
    Navigation
    1.29
    navigate
    1.21
     navig
    1.15
    navig
    1.12
     Navig
    1.08
    Navig
    1.05
    Navigate
    1.01
    Activations Density 0.009%

    No Known Activations