© 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. 24-GEMMASCOPE-RES-16K
    11. 5878
    Prev
    Next
    INDEX
    Explanations

    references to escape and evasion in a variety of contexts

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

    Avoiding negative outcomes

    np_acts-logits-general · gemini-2.0-flash

    facing opposition and danger

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     StatefulWidget
    -0.72
    createComponent
    -0.56
    enumii
    -0.56
     nahilalakip
    -0.54
    })}
    -0.53
    allowNull
    -0.52
    bukkit
    -0.52
    addPreferredGap
    -0.52
    Datuak
    -0.52
    viewDidLoad
    -0.51
    POSITIVE LOGITS
     scrutiny
    1.14
     criticism
    1.03
     attacks
    0.97
     onslaught
    0.92
     attack
    0.87
     ridicule
    0.87
     adversity
    0.84
     backlash
    0.81
     temptation
    0.81
     persecution
    0.80
    Activations Density 0.459%

    No Known Activations