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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7490
    Prev
    Next
    INDEX
    Explanations

    terms related to control systems and their mechanisms

    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
    ης
    -0.63
     pousser
    -0.62
    WEEN
    -0.61
     Ayers
    -0.61
     Akade
    -0.60
    brengen
    -0.60
     datter
    -0.60
     lèvres
    -0.59
     Mendez
    -0.59
     rump
    -0.59
    POSITIVE LOGITS
     control
    1.51
     CONTROL
    1.45
     controls
    1.43
     Control
    1.43
     Controls
    1.37
    control
    1.35
    Control
    1.32
    CONTROL
    1.26
    Controlling
    1.20
    Controls
    1.19
    Activations Density 0.084%

    No Known Activations