© 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. 10-GEMMASCOPE-RES-16K
    11. 9804
    Prev
    Next
    INDEX
    Explanations

    phrases related to standing up or standing out in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    })));
    -0.84
    "?>
    -0.80
    ');?>
    -0.80
     Ведь
    -0.80
    schra
    -0.79
     MTL
    -0.77
    :///
    -0.76
     miền
    -0.72
    theless
    -0.72
    ={`/
    -0.71
    POSITIVE LOGITS
     STAND
    1.55
     Stands
    1.52
     Stand
    1.51
    Stand
    1.48
     stand
    1.38
    STAND
    1.38
     stands
    1.38
     stood
    1.33
     standing
    1.25
    stands
    1.24
    Activations Density 0.047%

    No Known Activations