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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 6334
    Prev
    Next
    INDEX
    Explanations

    references to data formats and their specifications

    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
     CreateTagHelper
    -0.80
    Seeker
    -0.75
     calculées
    -0.72
     userService
    -0.70
    ($__
    -0.70
    voyance
    -0.70
    AnchorTagHelper
    -0.68
    onViewCreated
    -0.68
     AssemblyCompany
    -0.67
     Wilkes
    -0.67
    POSITIVE LOGITS
     format
    2.28
     FORMAT
    2.26
     Format
    2.18
     formats
    2.18
    Format
    2.10
    format
    2.08
     Formats
    2.03
    FORMAT
    2.02
    formats
    1.96
    Formats
    1.85
    Activations Density 0.068%

    No Known Activations