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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 16-GEMMASCOPE-RES-16K
    6. 6746
    Prev
    Next
    INDEX
    Explanations

    references to judicial candidates and their affiliations with political parties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Legal canons or bar associations

    np_acts-logits-general · gemini-2.0-flash

    judicial candidate discussions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     OnInit
    -0.53
    AutoScaleMode
    -0.52
     lenker
    -0.51
     MonoBehaviour
    -0.50
    UrlResolution
    -0.49
    Discografia
    -0.49
    Personensuche
    -0.48
    MemoryWarning
    -0.48
    IBOutlet
    -0.47
    łog
    -0.46
    POSITIVE LOGITS
     Lawyers
    1.11
     lawyers
    1.07
     attorneys
    1.05
     lawyer
    0.99
     Lawyer
    0.98
    lawyer
    0.96
     attorney
    0.94
     Attorneys
    0.91
    Lawyer
    0.91
    Attorney
    0.88
    Activations Density 1.073%

    No Known Activations