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. 14-GEMMASCOPE-RES-16K
    6. 13125
    Prev
    Next
    INDEX
    Explanations

    temporal references and indications of progression in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    %)$
    -0.77
     للاسماء
    -0.76
     ​​
    -0.76
    ]--;
    -0.72
    InputBorder
    -0.71
     McDonough
    -0.71
    исленность
    -0.70
    DataPropertyName
    -0.69
     FontWeight
    -0.68
    nestjs
    -0.68
    POSITIVE LOGITS
    later
    1.04
     Later
    0.99
     LATER
    0.99
    Later
    0.98
     later
    0.94
     ater
    0.80
    er
    0.77
     späteren
    0.76
     Earlier
    0.72
    sequent
    0.71
    Activations Density 0.063%

    No Known Activations