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

    Neuronpedia

    APICircuit 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. 5-GEMMASCOPE-RES-16K
    6. 1259
    Prev
    Next
    INDEX
    Explanations

    titles and positions related to political or governmental roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]")]
    -0.94
    styleType
    -0.92
    IsContent
    -0.90
    GEBURTSDATUM
    -0.78
     متعلقه
    -0.75
    AddTagHelper
    -0.75
    IsMutable
    -0.74
    UnknownFields
    -0.74
    Sucesor
    -0.71
    DebuggerStep
    -0.71
    POSITIVE LOGITS
     autrefois
    0.70
     formerly
    0.65
     früher
    0.57
     vroeger
    0.55
     once
    0.54
     former
    0.53
     tidligere
    0.53
     سابق
    0.52
    formerly
    0.52
     anteriormente
    0.52
    Activations Density 0.247%

    No Known Activations