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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 6557
    Prev
    Next
    INDEX
    Explanations

    legal terms and phrases related to criminal charges and legal proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    astify
    -0.77
    NgModule
    -0.76
    الحياه
    -0.73
     protoimpl
    -0.70
     виправивши
    -0.69
    SourceChecksum
    -0.69
     ProtoMessage
    -0.69
    ngdoc
    -0.68
    principalColumn
    -0.67
    SOUNDBITE
    -0.67
    POSITIVE LOGITS
     criminal
    1.08
     misdemeanor
    0.97
     DUI
    0.92
    criminal
    0.92
     Criminal
    0.89
     felony
    0.88
     court
    0.87
    Criminal
    0.86
     probation
    0.83
     crime
    0.76
    Activations Density 0.976%

    No Known Activations