© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 2065
    Prev
    Next
    INDEX
    Explanations

    technical discussions surrounding software design patterns and object management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.82
    ChildScrollView
    -0.64
    KommentareTeilen
    -0.59
    Utiliz
    -0.57
    transQ
    -0.52
     lenker
    -0.51
     Waray
    -0.51
     Utilizing
    -0.51
    ThroughAttribute
    -0.50
     lil
    -0.50
    POSITIVE LOGITS
     :-)
    0.74
     :-(
    0.72
     orthogonal
    0.72
     nontrivial
    0.69
     programmers
    0.66
     SOFTWARE
    0.65
     ;-)
    0.65
     invariants
    0.65
     jspb
    0.64
     programmer
    0.64
    Activations Density 1.380%

    No Known Activations