© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 2109
    Prev
    Next
    INDEX
    Explanations

    the conjunction "And"

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

    followed by a new point

    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
    ']):
    -0.61
    ')):
    -0.60
    %;">
    -0.60
    ()):
    -0.59
     but
    -0.57
    '}>
    -0.57
    etheless
    -0.57
    ();)
    -0.56
     '/':
    -0.55
     ]
    
    -0.55
    POSITIVE LOGITS
     yes
    0.97
     yeah
    0.96
     btw
    0.82
     sorry
    0.81
     BTW
    0.77
     FYI
    0.76
     remember
    0.76
     hey
    0.75
    yes
    0.75
     please
    0.73
    Activations Density 0.063%

    No Known Activations