© 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. 23-GEMMASCOPE-RES-16K
    11. 9489
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to holding or supporting something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Vidite
    -0.74
     Италијани
    -0.70
     defaultstate
    -0.63
     scolaires
    -0.63
    ukone
    -0.62
    JspWriter
    -0.62
    Carreira
    -0.61
     anledning
    -0.61
     Roskov
    -0.60
     المعيارى
    -0.60
    POSITIVE LOGITS
     onto
    1.12
     hold
    1.06
     sway
    1.03
    holds
    1.02
     accountable
    1.00
     holds
    0.92
    hold
    0.89
     hostage
    0.89
    HOLD
    0.87
     Hold
    0.86
    Activations Density 0.101%

    No Known Activations