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. 4-GEMMASCOPE-RES-16K
    6. 3483
    Prev
    Next
    INDEX
    Explanations

    references to distances, particularly in miles or kilometers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalTable
    -1.07
     Roskov
    -1.07
    IsMutable
    -1.06
     Réponses
    -1.05
    TintMode
    -1.01
    endpush
    -1.01
    sizeCache
    -0.94
    ItemBackground
    -0.90
     Bioaccumulative
    -0.89
    rrggbb
    -0.89
    POSITIVE LOGITS
     miles
    1.76
     inches
    1.56
    miles
    1.40
     pounds
    1.38
     mile
    1.32
    Miles
    1.24
     Miles
    1.24
     MILES
    1.21
     MILE
    1.19
     Inches
    1.19
    Activations Density 0.067%

    No Known Activations