© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 14270
    Prev
    Next
    INDEX
    Explanations

    references to legal counsel and issues related to 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 @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SourceChecksum
    -0.67
     république
    -0.63
    AddHtmlAttribute
    -0.61
    ulica
    -0.58
    HttpPut
    -0.58
    ]<<"
    -0.56
    denly
    -0.56
    pmd
    -0.56
    PONENTS
    -0.56
     وتسجيلات
    -0.56
    POSITIVE LOGITS
     counsel
    3.20
     Counsel
    3.01
     COUNSEL
    2.99
    Counsel
    2.76
     counseling
    2.73
    coun
    2.72
     counselling
    2.60
     Counseling
    2.58
     counselors
    2.48
     counsels
    2.39
    Activations Density 0.126%

    No Known Activations