Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 4583
    Prev
    Next
    INDEX
    Explanations

    references to legal representation and 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
    >({
    -0.63
     initWithFrame
    -0.63
    ագրություններ
    -0.59
    antd
    -0.58
     становника
    -0.56
    ]")]
    -0.56
    Measuring
    -0.54
    JsonFormat
    -0.54
    artifactId
    -0.54
    tplatz
    -0.53
    POSITIVE LOGITS
     attorneys
    1.20
     lawyers
    1.09
     attorney
    1.08
     lawyer
    1.06
     Lawyers
    0.96
     Attorneys
    0.94
     Lawyer
    0.92
     counsel
    0.92
    Lawyer
    0.88
     solicitor
    0.87
    Activations Density 0.374%

    No Known Activations