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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 15696
    Prev
    Next
    INDEX
    Explanations

    references to familial relationships and lineage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    KURZBESCHREIBUNG
    -0.51
     cesse
    -0.44
    стере
    -0.41
     ervan
    -0.40
     derived
    -0.39
    derived
    -0.38
    organizzazione
    -0.38
    0
    -0.38
    Copyright
    -0.38
    Name
    -0.37
    POSITIVE LOGITS
    EDEFAULT
    0.78
    +#+#
    0.77
    Tikang
    0.77
    DebuggerNonUser
    0.76
    aarrggbb
    0.69
    libft
    0.69
     XCTest
    0.68
     propOrder
    0.68
    олові
    0.68
    :+:
    0.67
    Activations Density 0.189%

    No Known Activations