© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 2249
    Prev
    Next
    INDEX
    Explanations

    indicators of leadership and organizational roles in counterterrorism efforts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    upcoming events and past actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BorderRadius
    -0.70
    +#+#
    -0.70
    BeginContext
    -0.69
    InputBorder
    -0.65
    RetentionPolicy
    -0.61
    #+#
    -0.60
    kloped
    -0.55
    +:+
    -0.49
    Embeddable
    -0.49
     möge
    -0.49
    POSITIVE LOGITS
     hopes
    0.96
     recently
    0.90
     expects
    0.87
     previously
    0.83
     hoped
    0.77
     anticipates
    0.77
     launched
    0.76
     intends
    0.75
     partnered
    0.74
     verwacht
    0.73
    Activations Density 0.079%

    No Known Activations