© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 9645
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to post-conviction relief processes and ineffective assistance of counsel

    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
    AutoresizingMask
    -0.77
    })));
    -0.77
     مرئيه
    -0.65
    ruik
    -0.59
    ilibrium
    -0.58
    참고
    -0.58
    ]));
    -0.58
     Martyn
    -0.57
    /></
    -0.57
     Tomar
    -0.56
    POSITIVE LOGITS
     convicted
    0.64
     sentencing
    0.57
     peniten
    0.57
     inmate
    0.55
     convicts
    0.52
    刑
    0.52
     pardoned
    0.52
     convict
    0.50
     condamné
    0.49
     Correctional
    0.49
    Activations Density 1.435%

    No Known Activations