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. 10468
    Prev
    Next
    INDEX
    Explanations

    references to months and dates

    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
    Personendaten
    -0.86
    StoreMessageInfo
    -0.78
    UserScript
    -0.77
    DockStyle
    -0.75
    IUrlHelper
    -0.74
     transfieras
    -0.72
    ksikon
    -0.71
    contentLoaded
    -0.69
    Попис
    -0.69
    oredCriteria
    -0.69
    POSITIVE LOGITS
     April
    1.12
     February
    1.08
     March
    1.04
     January
    1.03
     December
    1.02
    February
    0.99
    April
    0.99
     November
    0.96
     June
    0.95
     September
    0.94
    Activations Density 0.361%

    No Known Activations